@inproceedings{DBLP:conf/icml/McCallumS90, author = {Andrew McCallum and Kent A. Spackman}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallumS90}, booktitle = {Machine Learning, Proceedings of the Seventh International Conference on Machine Learning (ICML), Austin, Texas, USA, June 21-23, 1990}, editor = {Bruce W. Porter and Raymond J. Mooney}, pages = {149--152}, publisher = {Morgan Kaufmann}, timestamp = {Fri, 23 Dec 2011 00:00:00 +0100}, title = {Using Genetic Algorithms to Learn Disjunctive Rules from Examples}, year = {1990} } @inproceedings{DBLP:conf/icml/McCallum92, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallum92}, booktitle = {Proceedings of the Ninth International Workshop on Machine Learning ({ML} WS), Aberdeen, Scotland, UK, July 1-3, 1992}, editor = {Derek H. Sleeman and Peter Edwards}, pages = {316--321}, publisher = {Morgan Kaufmann}, timestamp = {Wed, 04 Dec 2002 15:40:32 +0100}, title = {Using Transitional Proximity for Faster Reinforcement Learning}, year = {1992} } @inproceedings{DBLP:conf/icml/McCallum93, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallum93}, booktitle = {Machine Learning, Proceedings of the Tenth International Conference, University of Massachusetts, Amherst, MA, USA, June 27-29, 1993}, pages = {190--196}, publisher = {Morgan Kaufmann}, timestamp = {Fri, 23 Dec 2011 00:00:00 +0100}, title = {Overcoming Incomplete Perception with Util Distinction Memory}, year = {1993} } @inproceedings{DBLP:conf/nips/McCallum94, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/McCallum94}, booktitle = {Advances in Neural Information Processing Systems 7, (NIPS), Denver, Colorado, USA}, editor = {Gerald Tesauro and David S. Touretzky and Todd K. Leen}, url = {http://papers.nips.cc/paper/932-instance-based-state-identification-for-reinforcement-learning}, pages = {377--384}, publisher = {{MIT} Press}, timestamp = {Thu, 11 Dec 2014 17:34:08 +0100}, title = {Instance-Based State Identification for Reinforcement Learning}, year = {1994} } @inproceedings{DBLP:conf/icml/McCallum95, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallum95}, booktitle = {Machine Learning, Proceedings of the Twelfth International Conference on Machine Learning, Tahoe City, California, USA, July 9-12, 1995}, editor = {Armand Prieditis and Stuart J. Russell}, pages = {387--395}, publisher = {Morgan Kaufmann}, timestamp = {Fri, 23 Dec 2011 00:00:00 +0100}, title = {Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State}, year = {1995} } @inproceedings{DBLP:conf/icml/McCallumN98, author = {Andrew McCallum and Kamal Nigam}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallumN98}, booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning ({ICML}), Madison, Wisconsin, USA, July 24-27, 1998}, editor = {Jude W. Shavlik}, pages = {350--358}, publisher = {Morgan Kaufmann}, timestamp = {Thu, 30 Jun 2011 10:34:12 +0200}, title = {Employing {EM} and Pool-Based Active Learning for Text Classification}, year = {1998} } @inproceedings{DBLP:conf/icml/McCallumRMN98, author = {Andrew McCallum and Ronald Rosenfeld and Tom M. Mitchell and Andrew Y. Ng}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallumRMN98}, booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning ({ICML}), Madison, Wisconsin, USA, July 24-27, 1998}, editor = {Jude W. Shavlik}, pages = {359--367}, publisher = {Morgan Kaufmann}, timestamp = {Thu, 30 Jun 2011 10:34:12 +0200}, title = {Improving Text Classification by Shrinkage in a Hierarchy of Classes}, year = {1998} } @inproceedings{DBLP:conf/aaai/NigamMTM98, author = {Kamal Nigam and Andrew McCallum and Sebastian Thrun and Tom M. Mitchell}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/NigamMTM98}, booktitle = {Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference ({AAAI}), July 26-30, 1998, Madison, Wisconsin, {USA.}}, editor = {Jack Mostow and Chuck Rich}, url = {http://www.aaai.org/Library/AAAI/1998/aaai98-112.php}, pages = {792--799}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Tue, 11 Dec 2012 00:00:00 +0100}, title = {Learning to Classify Text from Labeled and Unlabeled Documents}, year = {1998} } @inproceedings{DBLP:conf/sigir/BakerM98, author = {L. Douglas Baker and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/sigir/BakerM98}, booktitle = {{SIGIR} '98: Proceedings of the 21st Annual International {ACM} Conference on Research and Development in Information Retrieval ({SIGIR}), August 24-28 1998, Melbourne, Australia}, doi = {10.1145/290941.290970}, editor = {W. Bruce Croft and Alistair Moffat and C. J. van Rijsbergen and Ross Wilkinson and Justin Zobel}, url = {http://doi.acm.org/10.1145/290941.290970}, pages = {96--103}, publisher = {ACM}, timestamp = {Wed, 08 Feb 2017 13:37:23 +0100}, title = {Distributional Clustering of Words for Text Classification}, year = {1998} } @inproceedings{DBLP:conf/aaai/CravenFMMNS98, author = {Mark Craven and Dan DiPasquo and Dayne Freitag and Andrew McCallum and Tom M. Mitchell and Kamal Nigam and Se{\'{a}}n Slattery}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/CravenFMMNS98}, booktitle = {Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference ({AAAI}), July 26-30, 1998, Madison, Wisconsin, {USA.}}, editor = {Jack Mostow and Chuck Rich}, url = {http://www.aaai.org/Library/AAAI/1998/aaai98-072.php}, pages = {509--516}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Tue, 11 Dec 2012 00:00:00 +0100}, title = {Learning to Extract Symbolic Knowledge from the World Wide Web}, year = {1998} } @inproceedings{DBLP:conf/ijcai/McCallumNRS99, author = {Andrew McCallum and Kamal Nigam and Jason Rennie and Kristie Seymore}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ijcai/McCallumNRS99}, booktitle = {Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence ({IJCAI}) Stockholm, Sweden, July 31 - August 6, 1999. 2 Volumes, 1450 pages}, editor = {Thomas Dean}, url = {http://ijcai.org/Proceedings/99-2/Papers/001.pdf}, pages = {662--667}, publisher = {Morgan Kaufmann}, timestamp = {Tue, 19 Jul 2016 16:00:04 +0200}, title = {A Machine Learning Approach to Building Domain-Specific Search Engines}, year = {1999}, } @inproceedings{DBLP:conf/icml/RennieM99, author = {Jason Rennie and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/RennieM99}, booktitle = {Proceedings of the Sixteenth International Conference on Machine Learning ({ICML}), Bled, Slovenia, June 27 - 30, 1999}, editor = {Ivan Bratko and Saso Dzeroski}, pages = {335--343}, publisher = {Morgan Kaufmann}, timestamp = {Tue, 03 Dec 2002 12:31:12 +0100}, title = {Using Reinforcement Learning to Spider the Web Efficiently}, year = {1999} } @inproceedings{DBLP:conf/icml/McCallumFP00, author = {Andrew McCallum and Dayne Freitag and Fernando C. N. Pereira}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallumFP00}, booktitle = {Proceedings of the Seventeenth International Conference on Machine Learning ({ICML}), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000}, editor = {Pat Langley}, pages = {591--598}, publisher = {Morgan Kaufmann}, timestamp = {Sun, 21 Feb 2010 20:54:50 +0100}, title = {Maximum Entropy Markov Models for Information Extraction and Segmentation}, year = {2000} } @article{DBLP:journals/ir/McCallumNRS00, author = {Andrew McCallum and Kamal Nigam and Jason Rennie and Kristie Seymore}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ir/McCallumNRS00}, doi = {10.1023/A:1009953814988}, journal = {Inf. Retr.}, url = {https://doi.org/10.1023/A:1009953814988}, number = {2}, pages = {127--163}, timestamp = {Sat, 27 May 2017 01:00:00 +0200}, title = {Automating the Construction of Internet Portals with Machine Learning}, volume = {3}, year = {2000} } @inproceedings{DBLP:conf/kdd/McCallumNU00, author = {Andrew McCallum and Kamal Nigam and Lyle H. Ungar}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/McCallumNU00}, booktitle = {Proceedings of the sixth {ACM} international conference on Knowledge discovery and data mining ({SIGKDD}), Boston, MA, USA, August 20-23, 2000}, doi = {10.1145/347090.347123}, editor = {Raghu Ramakrishnan and Salvatore J. Stolfo and Roberto J. Bayardo and Ismail Parsa}, url = {http://doi.acm.org/10.1145/347090.347123}, pages = {169--178}, publisher = {ACM}, timestamp = {Wed, 12 Dec 2012 15:08:19 +0100}, title = {Efficient clustering of high-dimensional data sets with application to reference matching}, year = {2000} } @inproceedings{DBLP:conf/aaai/FreitagM00, author = {Dayne Freitag and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/FreitagM00}, booktitle = {Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on on Innovative Applications of Artificial Intelligence (AAAI), July 30 - August 3, 2000, Austin, Texas, {USA.}}, editor = {Henry A. Kautz and Bruce W. Porter}, url = {http://www.aaai.org/Library/AAAI/2000/aaai00-089.php}, pages = {584--589}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Tue, 11 Dec 2012 00:00:00 +0100}, title = {Information Extraction with {HMM} Structures Learned by Stochastic Optimization}, year = {2000} } @inproceedings{DBLP:conf/icml/ChangCM00, author = {Huan Chang and David Cohn and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/ChangCM00}, booktitle = {Proceedings of the Seventeenth International Conference on Machine Learning ({ICML}), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000}, editor = {Pat Langley}, pages = {127--134}, publisher = {Morgan Kaufmann}, timestamp = {Sun, 21 Feb 2010 20:54:50 +0100}, title = {Learning to Create Customized Authority Lists}, year = {2000} } @article{DBLP:journals/ml/NigamMTM00, author = {Kamal Nigam and Andrew McCallum and Sebastian Thrun and Tom M. Mitchell}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ml/NigamMTM00}, doi = {10.1023/A:1007692713085}, journal = {Machine Learning (ML)}, url = {https://doi.org/10.1023/A:1007692713085}, number = {2/3}, pages = {103--134}, timestamp = {Sun, 28 May 2017 01:00:00 +0200}, title = {Text Classification from Labeled and Unlabeled Documents using {EM}}, volume = {39}, year = {2000} } @article{DBLP:journals/ai/CravenDFMMNS00, author = {Mark Craven and Dan DiPasquo and Dayne Freitag and Andrew McCallum and Tom M. Mitchell and Kamal Nigam and Se{\'{a}}n Slattery}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ai/CravenDFMMNS00}, doi = {10.1016/S0004-3702(00)00004-7}, journal = {Artif. Intell.}, url = {https://doi.org/10.1016/S0004-3702(00)00004-7}, number = {1-2}, pages = {69--113}, timestamp = {Sat, 27 May 2017 01:00:00 +0200}, title = {Learning to construct knowledge bases from the World Wide Web}, volume = {118}, year = {2000} } @article{DBLP:journals/debu/CohenMQ00, author = {William W. Cohen and Andrew McCallum and Dallan Quass}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/debu/CohenMQ00}, journal = {{IEEE} Data Eng. Bull.}, url = {http://sites.computer.org/debull/A00SEP-CD.pdf}, number = {3}, pages = {17--24}, timestamp = {Wed, 19 Dec 2007 00:00:00 +0100}, title = {Learning to Understand the Web}, volume = {23}, year = {2000} } @inproceedings{DBLP:conf/icml/LaffertyMP01, author = {John D. Lafferty and Andrew McCallum and Fernando C. N. Pereira}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/LaffertyMP01}, booktitle = {Proceedings of the Eighteenth International Conference on Machine Learning ({ICML}), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001}, editor = {Carla E. Brodley and Andrea Pohoreckyj Danyluk}, pages = {282--289}, publisher = {Morgan Kaufmann}, timestamp = {Wed, 27 Nov 2002 10:53:35 +0100}, title = {Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data}, year = {2001}, sum = {A conditionally-trained model for sequences and other structured data, with global normalization. The original CRF paper. Don't bother reading the section on parameter estimation---use BFGS instead of Iterative Scaling; e.g. see [McCallum UAI 2003].} } @inproceedings{DBLP:conf/icml/RoyM01, author = {Nicholas Roy and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/RoyM01}, booktitle = {Proceedings of the Eighteenth International Conference on Machine Learning ({ICML}), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001}, editor = {Carla E. Brodley and Andrea Pohoreckyj Danyluk}, pages = {441--448}, publisher = {Morgan Kaufmann}, timestamp = {Wed, 27 Nov 2002 10:53:35 +0100}, title = {Toward Optimal Active Learning through Sampling Estimation of Error Reduction}, year = {2001}, sum = {A leave-one-out approach to active learning.} } @inproceedings{DBLP:conf/uai/BleiBM02, author = {David M. Blei and J. Andrew Bagnell and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/BleiBM02}, booktitle = {{UAI} '02, Proceedings of the 18th Conference in Uncertainty in Artificial Intelligence (UAI), University of Alberta, Edmonton, Alberta, Canada, August 1-4, 2002}, editor = {Adnan Darwiche and Nir Friedman}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=844&proceeding_id=18}, pages = {53--60}, publisher = {Morgan Kaufmann}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {Learning with Scope, with Application to Information Extraction and Classification}, year = {2002}, sum = {Learn highly reliable formatting-based extractors on the fly at test time, using graphical models and variational inference. Describes both generative and conditional versions of the model.} } @inproceedings{DBLP:conf/uai/McCallum03, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/McCallum03}, booktitle = {{UAI} '03, Proceedings of the 19th Conference in Uncertainty in Artificial Intelligence (UAI), Acapulco, Mexico, August 7-10 2003}, editor = {Christopher Meek and Uffe Kj{\ae}rulff}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=955&proceeding_id=19}, pages = {403--410}, publisher = {Morgan Kaufmann}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {Efficiently Inducing Features of Conditional Random Fields}, year = {2003}, sum = {CRFs give you the great power to include the kitchen sink worth of features. How do you decide which ones to include to avoid over-fitting and running out of memory? A formal, information-theoretic approach, with carefully-chosen approximations to make it efficient with millions of candidate features. This technique key to success in Hindi above, as well as work by Pereira's group at UPenn.} } @inproceedings{DBLP:conf/ijcai/McCallumW03, author = {Andrew McCallum and Ben Wellner}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ijcai/McCallumW03}, booktitle = {Proceedings of {IJCAI-03} Workshop on Information Integration on the Web (IIWeb-03), August 9-10, 2003, Acapulco, Mexico}, editor = {Subbarao Kambhampati and Craig A. Knoblock}, url = {http://www.isi.edu/info-agents/workshops/ijcai03/papers/McCallum-ijcaiws.pdf}, pages = {79--84}, timestamp = {Wed, 21 Jul 2004 13:31:29 +0200}, title = {Toward Conditional Models of Identity Uncertainty with Application to Proper Noun Coreference}, year = {2003}, sum = {A conditionally-trained model of object consolidation, based on graph partitioning with learned edge weights.} } @inproceedings{DBLP:conf/conll/McCallum003, author = {Andrew McCallum and Wei Li}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/conll/McCallum003}, booktitle = {Proceedings of the Seventh Conference on Natural Language Learning (CoNLL 2003), Held in cooperation with {HLT-NAACL} 2003, Edmonton, Canada, May 31 - June 1, 2003}, editor = {Walter Daelemans and Miles Osborne}, url = {http://aclweb.org/anthology/W/W03/W03-0430.pdf}, pages = {188--191}, publisher = {ACL}, timestamp = {Fri, 23 Jan 2015 14:28:25 +0100}, title = {Early results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons}, year = {2003}, sum = {This is the first publication about named entity extraction with CRFs.} } @inproceedings{DBLP:conf/dgo/PintoMWC03, author = {David Pinto and Andrew McCallum and Xing Wei and W. Bruce Croft}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/dgo/PintoMWC03}, booktitle = {Proceedings of the 2003 Annual National Conference on Digital Government Research ({DG.O}), 2003}, editor = {Yigal Arens and Eduard H. Hovy and Peggy Agouris}, url = {http://dl.acm.org/citation.cfm?id=1123294}, publisher = {Digital Government Research Center}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Fri, 20 Nov 2015 13:56:20 +0100}, title = {Table Extraction Using Conditional Random Fields}, year = {2003}, } @inproceedings{DBLP:conf/sigir/PintoMWC03, author = {David Pinto and Andrew McCallum and Xing Wei and W. Bruce Croft}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/sigir/PintoMWC03}, booktitle = {{SIGIR} 2003: Proceedings of the 26th Annual International {ACM} Conference on Research and Development in Information Retrieval ({SIGIR}), July 28 - August 1, 2003, Toronto, Canada}, doi = {10.1145/860435.860479}, editor = {Charles L. A. Clarke and Gordon V. Cormack and Jamie Callan and David Hawking and Alan F. Smeaton}, url = {http://doi.acm.org/10.1145/860435.860479}, pages = {235--242}, publisher = {ACM}, timestamp = {Wed, 08 Feb 2017 13:37:23 +0100}, title = {Table extraction using conditional random fields}, year = {2003}, sum = {Application of CRFs to finding tables in government reports. Uses both language and layout features.} } @article{DBLP:journals/sigir/AllanABBCCDFHHHHHKLLLLMMPPRRRRRSSSSTVWXZ03, author = {James Allan and Jay Aslam and Nicholas J. Belkin and Chris Buckley and James P. Callan and W. Bruce Croft and Susan T. Dumais and Norbert Fuhr and Donna Harman and David J. Harper and Djoerd Hiemstra and Thomas Hofmann and Eduard H. Hovy and Wessel Kraaij and John D. Lafferty and Victor Lavrenko and David D. Lewis and Liz Liddy and R. Manmatha and Andrew McCallum and Jay M. Ponte and John M. Prager and Dragomir R. Radev and Philip Resnik and Stephen E. Robertson and Ronald Rosenfeld and Salim Roukos and Mark Sanderson and Richard M. Schwartz and Amit Singhal and Alan F. Smeaton and Howard R. Turtle and Ellen M. Voorhees and Ralph M. Weischedel and Jinxi Xu and ChengXiang Zhai}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/sigir/AllanABBCCDFHHHHHKLLLLMMPPRRRRRSSSSTVWXZ03}, doi = {10.1145/945546.945549}, journal = {{SIGIR} Forum}, url = {http://doi.acm.org/10.1145/945546.945549}, number = {1}, pages = {31--47}, timestamp = {Wed, 19 Sep 2012 01:00:00 +0200}, title = {Challenges in information retrieval and language modeling: report of a workshop held at the center for intelligent information retrieval, University of Massachusetts Amherst, September 2002}, volume = {37}, year = {2003}, sum = {A report about fruitful areas for future work in IR over a five-year time scale.} } @inproceedings{DBLP:conf/nips/RainaSNM03, author = {Rajat Raina and Yirong Shen and Andrew Y. Ng and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/RainaSNM03}, booktitle = {Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems ({NIPS}), December 8-13, 2003, Vancouver and Whistler, British Columbia, Canada]}, editor = {Sebastian Thrun and Lawrence K. Saul and Bernhard Sch{\"{o}}lkopf}, url = {http://papers.nips.cc/paper/2405-classification-with-hybrid-generativediscriminative-models}, pages = {545--552}, publisher = {{MIT} Press}, timestamp = {Thu, 11 Dec 2014 17:34:07 +0100}, title = {Classification with Hybrid Generative/Discriminative Models}, year = {2003}, sum = {Train some parameters generatively, some parameters conditionally.} } @article{DBLP:journals/talip/LiM03, author = {Wei Li and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/talip/LiM03}, doi = {10.1145/979872.979879}, journal = {{ACM} Trans. Asian Lang. Inf. Process.}, url = {http://doi.acm.org/10.1145/979872.979879}, number = {3}, pages = {290--294}, timestamp = {Thu, 19 Aug 2010 01:00:00 +0200}, title = {Rapid development of Hindi named entity recognition using conditional random fields and feature induction}, volume = {2}, year = {2003}, sum = {How we developed a named entity recognition system for Hindi in just a few weeks.} } @inproceedings{DBLP:conf/nips/McCallumW04, author = {Andrew McCallum and Ben Wellner}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/McCallumW04}, booktitle = {Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems ({NIPS}), December 13-18, 2004, Vancouver, British Columbia, Canada]}, url = {http://papers.nips.cc/paper/2557-conditional-models-of-identity-uncertainty-with-application-to-noun-coreference}, pages = {905--912}, timestamp = {Thu, 11 Dec 2014 17:34:07 +0100}, title = {Conditional Models of Identity Uncertainty with Application to Noun Coreference}, year = {2004}, sum = {A model of object consolidation, based on graph partitioning with learned edge weights. Conference paper version of 2003 work in KDD Workshop on Data Cleaning.} } @inproceedings{DBLP:conf/ceas/CulottaBM04, author = {Aron Culotta and Ron Bekkerman and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ceas/CulottaBM04}, booktitle = {{CEAS} 2004 - First Conference on Email and Anti-Spam (CEAS), July 30-31, 2004, Mountain View, California, {USA}}, url = {http://www.ceas.cc/papers-2004/176.pdf}, timestamp = {Fri, 02 Jun 2006 13:30:15 +0200}, title = {Extracting social networks and contact information from email and the Web}, year = {2004}, sum = {Describes an early version of an end-to-end system that automatically populates your email address book with a large social network, including "friends-of-friends," and information about people's expertise.} } @inproceedings{DBLP:conf/uai/WellnerMPH04, author = {Ben Wellner and Andrew McCallum and Fuchun Peng and Michael Hay}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/WellnerMPH04}, booktitle = {{UAI} '04, Proceedings of the 20th Conference in Uncertainty in Artificial Intelligence (UAI), Banff, Canada, July 7-11, 2004}, editor = {David Maxwell Chickering and Joseph Y. Halpern}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1158&proceeding_id=20}, pages = {593--601}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {An Integrated, Conditional Model of Information Extraction and Coreference with Appli}, year = {2004}, sum = {A conditionally-trained graphical model for identity uncertainty in relational domains, representing mentions, entities and their attributes. Also a first example of joint inference for extraction and identity uncertainty--coreference decisions actually integrate out uncertainty about information extraction.} } @inproceedings{DBLP:conf/icml/SuttonRM04, author = {Charles A. Sutton and Khashayar Rohanimanesh and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/SuttonRM04}, booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference ({ICML}), Banff, Alberta, Canada, July 4-8, 2004}, doi = {10.1145/1015330.1015422}, editor = {Carla E. Brodley}, url = {http://doi.acm.org/10.1145/1015330.1015422}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Mon, 22 Oct 2007 13:54:01 +0200}, title = {Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data}, volume = {69}, year = {2004}, sum = {Joint inference over two traditionally-separate layers of NLP processing: POS-tagging and NP-chunking. Introduces the CRF analogue of Factorial HMMs. Compares several approximate inference procedures.} } @inproceedings{DBLP:conf/naacl/PengM04, author = {Fuchun Peng and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/PengM04}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics ({HLT-NAACL}), Boston, Massachusetts, USA, May 2-7, 2004}, editor = {Julia Hirschberg and Susan T. Dumais and Daniel Marcu and Salim Roukos}, url = {http://aclweb.org/anthology/N/N04/N04-1042.pdf}, pages = {329--336}, publisher = {The Association for Computational Linguistics}, timestamp = {Mon, 19 Dec 2016 00:00:00 +0100}, title = {Accurate Information Extraction from Research Papers using Conditional Random Fields}, year = {2004}, sum = {Applies CRFs to extraction from research paper headers and reference sections, to obtain current best-in-the-world accuracy. Also compares some simple regularization methods.} } @inproceedings{DBLP:conf/coling/PengFM04, author = {Fuchun Peng and Fangfang Feng and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/coling/PengFM04}, booktitle = {{COLING} 2004, 20th International Conference on Computational Linguistics, Proceedings of the Conference (COLING), 23-27 August 2004, Geneva, Switzerland}, url = {http://www.aclweb.org/anthology/C04-1081}, timestamp = {Mon, 04 Mar 2013 20:57:23 +0100}, title = {Chinese Segmentation and New Word Detection using Conditional Random Fields}, year = {2004}, sum = {State-of-the art Chinese word segmentation with CRFs, with rich features and many lexicons; also using confidence estimation to add new words to the lexicon.} } @inproceedings{DBLP:conf/aaai/KristjanssonCVM04, author = {Trausti T. Kristjansson and Aron Culotta and Paul A. Viola and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/KristjanssonCVM04}, booktitle = {Proceedings of the Nineteenth National Conference on Artificial Intelligence, Sixteenth Conference on Innovative Applications of Artificial Intelligence (AAAI), July 25-29, 2004, San Jose, California, {USA}}, editor = {Deborah L. McGuinness and George Ferguson}, url = {http://www.aaai.org/Library/AAAI/2004/aaai04-066.php}, pages = {412--418}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Tue, 11 Dec 2012 00:00:00 +0100}, title = {Interactive Information Extraction with Constrained Conditional Random Fields}, year = {2004}, desc = {Winner of Honorable Mention Award}, sum = {Help a user interactively correct the results of extraction by providing uncertainty cues in the UI, and by using constrained Viterbi to automatically make additional corrections after the first human correction.} } @article{DBLP:journals/queue/McCallum05, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/queue/McCallum05}, doi = {10.1145/1105664.1105679}, journal = {{ACM} Queue}, url = {http://doi.acm.org/10.1145/1105664.1105679}, number = {9}, pages = {48--57}, timestamp = {Thu, 16 Mar 2006 00:00:00 +0100}, title = {Information extraction: distilling structured data from unstructured text}, volume = {3}, year = {2005}, sum = {An overview of information extraction by machine learning methods, written for people not familiar with machine learning, especially CTOs and other people in business.} } @inproceedings{DBLP:conf/ijcai/McCallumCW05, author = {Andrew McCallum and Andr{\'{e}}s Corrada{-}Emmanuel and Xuerui Wang}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ijcai/McCallumCW05}, booktitle = {IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), Edinburgh, Scotland, UK, July 30 - August 5, 2005}, editor = {Leslie Pack Kaelbling and Alessandro Saffiotti}, url = {http://ijcai.org/Proceedings/05/Papers/1623.pdf}, pages = {786--791}, publisher = {Professional Book Center}, timestamp = {Wed, 20 Jul 2016 09:10:46 +0200}, title = {Topic and Role Discovery in Social Networks}, year = {2005}, sum = {Conference paper version of tech report by same authors in 2004 below. Also includes new results with Role-Author-Recipient-Topic model. Discover roles by social network analysis with a Bayesian network that models both links and text messages exchanged on those links. Experiments with Enron email and academic email.} } @inproceedings{DBLP:conf/uai/McCallumBP05, author = {Andrew McCallum and Kedar Bellare and Fernando C. N. Pereira}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/McCallumBP05}, booktitle = {{UAI} '05, Proceedings of the 21st Conference in Uncertainty in Artificial Intelligence (UAI), Edinburgh, Scotland, July 26-29, 2005}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1176&proceeding_id=21}, pages = {388--395}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {A Conditional Random Field for Discriminatively-trained Finite-state String Edit Distance}, year = {2005}, sum = {Train a string edit distance function from both positive and negative examples of string pairs (matching and mismatching). Significantly, the model designer is free to use arbitrary, fancy features of both strings, and also very flexible edit operations. This model is an example of an increasingly popular interesting class---conditionally-trained models with latent variables. Positive results on citations, addresses and names.} } @inproceedings{DBLP:conf/cikm/CulottaM05, author = {Aron Culotta and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/CulottaM05}, booktitle = {Proceedings of the 2005 {ACM} International Conference on Information and Knowledge Management ({CIKM}), Bremen, Germany, October 31 - November 5, 2005}, doi = {10.1145/1099554.1099615}, editor = {Otthein Herzog and Hans{-}J{\"{o}}rg Schek and Norbert Fuhr and Abdur Chowdhury and Wilfried Teiken}, url = {http://doi.acm.org/10.1145/1099554.1099615}, pages = {257--258}, publisher = {ACM}, timestamp = {Fri, 10 Feb 2006 00:00:00 +0100}, title = {Joint deduplication of multiple record types in relational data}, year = {2005}, sum = {Longer Tech Report version: A Conditional Model of Deduplication for Multi-type Relational Data. Technical Report IR-443, University of Massachusetts, September 2005.} } @inproceedings{DBLP:conf/aaai/CulottaM05, author = {Aron Culotta and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/CulottaM05}, booktitle = {Proceedings, The Twentieth National Conference on Artificial Intelligence and the Seventeenth Innovative Applications of Artificial Intelligence Conference (AAAI), July 9-13, 2005, Pittsburgh, Pennsylvania, {USA}}, editor = {Manuela M. Veloso and Subbarao Kambhampati}, url = {http://www.aaai.org/Library/AAAI/2005/aaai05-117.php}, pages = {746--751}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Mon, 10 Dec 2012 00:00:00 +0100}, title = {Reducing Labeling Effort for Structured Prediction Tasks}, year = {2005}, sum = {A step toward bringing trainable information extraction to the masses! Make it easier for end-users to train IE by providing multiple-choice labeling options, and propagating any constraints their labels provide on portions of the record-labeling task.} } @inproceedings{DBLP:conf/naacl/SuttonM05, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/SuttonM05}, booktitle = {{HLT/EMNLP} 2005, Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP), Proceedings of the Conference, 6-8 October 2005, Vancouver, British Columbia, Canada}, url = {http://aclweb.org/anthology/H/H05/H05-1094.pdf}, pages = {748--754}, publisher = {The Association for Computational Linguistics}, timestamp = {Mon, 19 Dec 2016 00:00:00 +0100}, title = {Composition of Conditional Random Fields for Transfer Learning}, year = {2005}, sum = {Improve information extraction from email data by using the output of another extractor that was trained on large quantities of newswire. Improve accuracy further by using joint inference between the two tasks---so that the final target task can actually affect the output of the intermediate task.} } @inproceedings{DBLP:conf/conll/SuttonM05, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/conll/SuttonM05}, booktitle = {Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL), Ann Arbor, Michigan, USA, June 29-30, 2005}, editor = {Ido Dagan and Daniel Gildea}, url = {http://aclweb.org/anthology/W/W05/W05-0636.pdf}, pages = {225--228}, publisher = {ACL}, timestamp = {Fri, 23 Jan 2015 14:19:48 +0100}, title = {Joint Parsing and Semantic Role Labeling}, year = {2005}, sum = {Attempt to improve accuracy by performing joint inference over parsing and semantic role labeling---preserving uncertainty and multiple hypotheses in Dan Bikel's parser. Unfortunately the effort yielded negative results, most likely because the components needed to produce better calibrated probabilities.} } @inproceedings{DBLP:conf/uai/SuttonM05, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/SuttonM05}, booktitle = {{UAI} '05, Proceedings of the 21st Conference in Uncertainty in Artificial Intelligence (UAI), Edinburgh, Scotland, July 26-29, 2005}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1182&proceeding_id=21}, pages = {568--575}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {Piecewise Training for Undirected Models}, year = {2005}, sum = {Efficiently train a large graphical model in separately normalized pieces, and amazingly often obtain higher accuracy than without this approximation. This paper also shows that this piecewise objective is a lower bound on the exact likelihood, and gives results with three different graphical model structures.} } @inproceedings{DBLP:conf/cikm/GhamrawiM05, author = {Nadia Ghamrawi and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/GhamrawiM05}, booktitle = {Proceedings of the 2005 {ACM} International Conference on Information and Knowledge Management ({CIKM}), Bremen, Germany, October 31 - November 5, 2005}, doi = {10.1145/1099554.1099591}, editor = {Otthein Herzog and Hans{-}J{\"{o}}rg Schek and Norbert Fuhr and Abdur Chowdhury and Wilfried Teiken}, url = {http://doi.acm.org/10.1145/1099554.1099591}, pages = {195--200}, publisher = {ACM}, timestamp = {Fri, 10 Feb 2006 00:00:00 +0100}, title = {Collective multi-label classification}, year = {2005}, sum = {Multi-label document classification with a conditional maximum entropy model that captures not only the traditional dependences between words and the class labels, but also the coocurrence dependencies between the class labels. Performs joint inference among all class labels.} } @inproceedings{DBLP:conf/www/BekkermanM05, author = {Ron Bekkerman and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/www/BekkermanM05}, booktitle = {Proceedings of the 14th international conference on World Wide Web ({WWW}), Chiba, Japan, May 10-14, 2005}, doi = {10.1145/1060745.1060813}, editor = {Allan Ellis and Tatsuya Hagino}, url = {http://doi.acm.org/10.1145/1060745.1060813}, pages = {463--470}, publisher = {ACM}, timestamp = {Fri, 10 Feb 2006 00:00:00 +0100}, title = {Disambiguating Web appearances of people in a social network}, year = {2005}, sum = {Find homepages and other Web pages mentioning particular people. Do a better job by leveraging a collection of related people.} } @inproceedings{DBLP:conf/icml/BekkermanEM05, author = {Ron Bekkerman and Ran El{-}Yaniv and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/BekkermanEM05}, booktitle = {Machine Learning, Proceedings of the Twenty-Second International Conference ({ICML}), Bonn, Germany, August 7-11, 2005}, doi = {10.1145/1102351.1102357}, editor = {Luc De Raedt and Stefan Wrobel}, url = {http://doi.acm.org/10.1145/1102351.1102357}, pages = {41--48}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Mon, 22 Oct 2007 13:52:21 +0200}, title = {Multi-way distributional clustering via pairwise interactions}, volume = {119}, year = {2005}, sum = {Distributional clustering in multiple feature dimensions or modalities at once--made efficient by a factored representation as used in graphical models, and by a combination of top-down and bottom-up clustering. Results on email clustering, and new best results on 20 Newsgroups.} } @inproceedings{DBLP:conf/aaai/LiM05, author = {Wei Li and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/LiM05}, booktitle = {Proceedings, The Twentieth National Conference on Artificial Intelligence and the Seventeenth Innovative Applications of Artificial Intelligence Conference (AAAI), July 9-13, 2005, Pittsburgh, Pennsylvania, {USA}}, editor = {Manuela M. Veloso and Subbarao Kambhampati}, url = {http://www.aaai.org/Library/AAAI/2005/aaai05-128.php}, pages = {813--818}, publisher = {{AAAI} Press / The {MIT} Press}, timestamp = {Mon, 10 Dec 2012 00:00:00 +0100}, title = {Semi-Supervised Sequence Modeling with Syntactic Topic Models}, year = {2005}, sum = {Learn a low-dimensional manifold from large quantities of unlabled text data, then use components of the manifold as additional features when training a linear-chain CRF with limited labeled data. The manifold is learned using HMM-LDA [Griffiths, Steyvers, Blei, Tenenbaum 2004], an unsupervised model with special structure suitable for sequences and topics. Experimens with English part-of-speech tagging and Chinese word segmentation.} } @inproceedings{DBLP:conf/kdd/WangMM05, author = {Xuerui Wang and Natasha Mohanty and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/WangMM05}, booktitle = {Proceedings of the 3rd international workshop on Link discovery (LinkKDD), Chicago, Illinois, USA, August 21-25, 2005}, doi = {10.1145/1134271.1134276}, editor = {Jafar Adibi and Marko Grobelnik and Dunja Mladenic and Patrick Pantel}, url = {http://doi.acm.org/10.1145/1134271.1134276}, pages = {28--35}, publisher = {ACM}, timestamp = {Mon, 07 Sep 2015 13:38:15 +0200}, title = {Group and topic discovery from relations and text}, year = {2005}, sum = {Social network analysis that simultaneously discovers groups of entities and also clusters attributes of their relations, such that clustering in each dimension informs the other. Applied to the voting records and corresponding text of resolutions from the U.S. Senate and the U.N., showing that incorporating the votes results in more salient topic clusters, and that different groupings of legislators emerge from different topics.} } @inproceedings{DBLP:conf/nips/WangMM05, author = {Xuerui Wang and Natasha Mohanty and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/WangMM05}, booktitle = {Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems ({NIPS}), December 5-8, 2005, Vancouver, British Columbia, Canada]}, url = {http://papers.nips.cc/paper/2820-group-and-topic-discovery-from-relations-and-their-attributes}, pages = {1449--1456}, timestamp = {Thu, 11 Dec 2014 17:34:08 +0100}, title = {Group and Topic Discovery from Relations and Their Attributes}, year = {2005}, sum = {Social network analysis that simultaneously discovers groups of entities and also clusters attributes of their relations, such that clustering in each dimension informs the other. Applied to the voting records and corresponding text of resolutions from the U.S. Senate and the U.N., showing that incorporating the votes results in more salient topic clusters, and that different groupings of legislators emerge from different topics.} } @inproceedings{DBLP:conf/imc/GuMT05, author = {Yu Gu and Andrew McCallum and Donald F. Towsley}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/imc/GuMT05}, booktitle = {Proceedings of the 5th Internet Measurement Conference ({IMC}), Berkeley, California, USA, October 19-21, 2005}, url = {http://www.usenix.org/events/imc05/tech/gu.html}, pages = {345--350}, publisher = {{USENIX} Association}, timestamp = {Sat, 19 Aug 2017 20:08:45 +0200}, title = {Detecting Anomalies in Network Traffic Using Maximum Entropy Estimation}, year = {2005}, sum = {Build a density model of normal Internet traffic with Maximum Entropy and feature induction. Detect network attacks by density threshold.} } @inproceedings{DBLP:conf/kdd/McCallum06, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/McCallum06}, booktitle = {Proceedings of the Twelfth {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Philadelphia, PA, USA, August 20-23, 2006}, doi = {10.1145/1150402.1150515}, editor = {Tina Eliassi{-}Rad and Lyle H. Ungar and Mark Craven and Dimitrios Gunopulos}, url = {http://doi.acm.org/10.1145/1150402.1150515}, pages = {835}, publisher = {ACM}, timestamp = {Wed, 20 Dec 2006 14:06:10 +0100}, title = {Information extraction, data mining and joint inference}, year = {2006} } @inproceedings{DBLP:conf/aaai/McCallumPDW06, author = {Andrew McCallum and Chris Pal and Gregory Druck and Xuerui Wang}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/aaai/McCallumPDW06}, booktitle = {Proceedings, The Twenty-First National Conference on Artificial Intelligence and the Eighteenth Innovative Applications of Artificial Intelligence Conference (AAAI), July 16-20, 2006, Boston, Massachusetts, {USA}}, url = {http://www.aaai.org/Library/AAAI/2006/aaai06-069.php}, pages = {433--439}, publisher = {{AAAI} Press}, timestamp = {Mon, 19 Mar 2012 00:00:00 +0100}, title = {Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification}, year = {2006}, sum = {Estimate parameters of an undirected graphical model not by joint likelihood, or conditional likelihood, but by a product of multiple conditional likelihoods. Can act as an improved regularizer. With latent variables, can cluster structured, relational data, like Latent Dirichlet Allocation and its successors, but with undirected graphical models and (cross-cutting) conditional-training. Improved results on document classification, Jebara-inspired synthetic data, and over the Harmonium as tested on an information retreival task.} } @inproceedings{DBLP:conf/icml/McCallumWM06, author = {Andrew McCallum and Xuerui Wang and Natasha Mohanty}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/McCallumWM06}, booktitle = {Statistical Network Analysis: Models, Issues, and New Directions - {ICML} 2006 Workshop on Statistical Network Analysis (ICML WS), Pittsburgh, PA, USA, June 29, 2006, Revised Selected Papers}, doi = {10.1007/978-3-540-73133-7_3}, editor = {Edoardo M. Airoldi and David M. Blei and Stephen E. Fienberg and Anna Goldenberg and Eric P. Xing and Alice X. Zheng}, url = {https://doi.org/10.1007/978-3-540-73133-7_3}, pages = {28--44}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {Sun, 04 Jun 2017 10:09:08 +0200}, title = {Joint Group and Topic Discovery from Relations and Text}, volume = {4503}, year = {2006} } @inproceedings{DBLP:conf/naacl/CulottaMB06, author = {Aron Culotta and Andrew McCallum and Jonathan Betz}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/CulottaMB06}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings (HLT/NAACL), June 4-9, 2006, New York, New York, {USA}}, editor = {Robert C. Moore and Jeff A. Bilmes and Jennifer Chu{-}Carroll and Mark Sanderson}, url = {http://aclweb.org/anthology/N/N06/N06-1038.pdf}, publisher = {The Association for Computational Linguistics}, timestamp = {Mon, 19 Dec 2016 00:00:00 +0100}, title = {Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text}, year = {2006}, sum = {Extract relations from Wikipedia articles. Run data mining on the relational graph to obtain patterns that are predictive of relations---such as "opponent of my opponent is my ally" and "a person is likely to have the same religion as their parents." Then use feaures derived from these patterns in a second run of extraction that improves accuracy.} } @article{DBLP:journals/ai/CulottaKMV06, author = {Aron Culotta and Trausti T. Kristjansson and Andrew McCallum and Paul A. Viola}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ai/CulottaKMV06}, doi = {10.1016/j.artint.2006.08.001}, journal = {Artif. Intell.}, url = {https://doi.org/10.1016/j.artint.2006.08.001}, number = {14-15}, pages = {1101--1122}, timestamp = {Sat, 27 May 2017 01:00:00 +0200}, title = {Corrective feedback and persistent learning for information extraction}, volume = {170}, year = {2006}, sum = {Help a user interactively correct the results of extraction by providing uncertainty cues in the UI, and by using constrained Viterbi to automatically make additional corrections after the first human correction. Journal paper version of AAAI paper by the same authors. Adds experiments with active learning.} } @inproceedings{DBLP:conf/icpr/KelmPM06, author = {B. Michael Kelm and Chris Pal and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icpr/KelmPM06}, booktitle = {18th International Conference on Pattern Recognition ({ICPR}), 20-24 August 2006, Hong Kong, China}, doi = {10.1109/ICPR.2006.384}, url = {https://doi.org/10.1109/ICPR.2006.384}, pages = {828--832}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 24 May 2017 01:00:00 +0200}, title = {Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning}, year = {2006}, sum = {Multi-conditional learning explored in the context of computer vision.} } @inproceedings{DBLP:conf/naacl/SuttonSM06, author = {Charles A. Sutton and Michael Sindelar and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/SuttonSM06}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Proceedings, June 4-9, 2006, New York, New York, {USA}}, editor = {Robert C. Moore and Jeff A. Bilmes and Jennifer Chu{-}Carroll and Mark Sanderson}, url = {http://aclweb.org/anthology/N/N06/N06-1012.pdf}, publisher = {The Association for Computational Linguistics}, timestamp = {Mon, 19 Dec 2016 00:00:00 +0100}, title = {Reducing Weight Undertraining in Structured Discriminative Learning}, year = {2006}, sum = {Train separately CRFs with different subsets of the features, then integrate them at test time---four different variations on the method. Especially make more reliable use of lexicon features and other highly-predictable but brittle features.} } @inproceedings{DBLP:conf/icassp/PalSM06, author = {Chris Pal and Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icassp/PalSM06}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing ({ICASSP}), Toulouse, France, May 14-19, 2006}, doi = {10.1109/ICASSP.2006.1661342}, url = {https://doi.org/10.1109/ICASSP.2006.1661342}, pages = {581--584}, publisher = {IEEE}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, title = {Sparse Forward-Backward Using Minimum Divergence Beams for Fast Training Of Conditional Random Fields}, year = {2006}, sum = {An alternative method for beam-search based on variational principles. Enables not only faster test-time performance of large-state-space CRFs, but this method makes beam search robust enough to be used at training time, enabling dramatically faster learning of discriminative finite-state methods for speech, IE and other applications.} } @article{DBLP:journals/ipm/PengM06, author = {Fuchun Peng and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ipm/PengM06}, doi = {10.1016/j.ipm.2005.09.002}, journal = {Inf. Process. Manage.}, url = {https://doi.org/10.1016/j.ipm.2005.09.002}, number = {4}, pages = {963--979}, timestamp = {Thu, 18 May 2017 01:00:00 +0200}, title = {Information extraction from research papers using conditional random fields}, volume = {42}, year = {2006} } @inproceedings{DBLP:conf/jcdl/MannMM06, author = {Gideon S. Mann and David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/jcdl/MannMM06}, booktitle = {{ACM/IEEE} Joint Conference on Digital Libraries ({JCDL}), Chapel Hill, NC, USA, June 11-15, 2006, Proceedings}, doi = {10.1145/1141753.1141765}, editor = {Gary Marchionini and Michael L. Nelson and Catherine C. Marshall}, url = {http://doi.acm.org/10.1145/1141753.1141765}, pages = {65--74}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Bibliometric impact measures leveraging topic analysis}, year = {2006}, sum = {Use a new topic model that leverages n-grams to discover interpretable, fine-grained topics in over a million research papers. Use these topic divisions as well as automated citation analysis to extend three existing bibliometric impact measures, and create three new ones: Topical Diversity, Topical Transfer, Topical Precedence.} } @inproceedings{DBLP:conf/emnlp/WickCM06, author = {Michael L. Wick and Aron Culotta and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/WickCM06}, booktitle = {{EMNLP} 2007, Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP), 22-23 July 2006, Sydney, Australia}, editor = {Dan Jurafsky and {\'{E}}ric Gaussier}, url = {http://www.aclweb.org/anthology/W06-1671}, pages = {603--611}, publisher = {ACL}, timestamp = {Wed, 23 Jun 2010 10:51:58 +0200}, title = {Learning Field Compatibilities to Extract Database Records from Unstructured Text}, year = {2006}, sum = {Record extraction, jointly accounting for multi-field compatibility by content and layout features.} } @inproceedings{DBLP:conf/dial/FengMM06, author = {Shaolei Feng and R. Manmatha and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/dial/FengMM06}, booktitle = {Second International Workshop on Document Image Analysis for Libraries ({DIAL}), 27-28 April 2006, Lyon, France}, doi = {10.1109/DIAL.2006.19}, url = {https://doi.org/10.1109/DIAL.2006.19}, pages = {30--37}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 26 May 2017 01:00:00 +0200}, title = {Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition}, year = {2006}, sum = {Mixed results on CRFs applied to handwritten word recognition.} } @inproceedings{DBLP:conf/icml/LiM06, author = {Wei Li and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/LiM06}, booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference ({ICML}), Pittsburgh, Pennsylvania, USA, June 25-29, 2006}, doi = {10.1145/1143844.1143917}, editor = {William W. Cohen and Andrew Moore}, url = {http://doi.acm.org/10.1145/1143844.1143917}, pages = {577--584}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Thu, 19 Aug 2010 01:00:00 +0200}, title = {Pachinko allocation: DAG-structured mixture models of topic correlations}, volume = {148}, year = {2006}, sum = {An LDA-style topic model that captures correlations between topics, enabling discovery of finer-grained topics. Similar motivations to Blei and Lafferty's Correlated Topic Model (CTM), but uses a DAG to capture arbitrary, nested and possibly sparse correlations among topics. Interior nodes of the DAG have a Dirichlet distribution over their children; words are in the leaves. Provides improved interpretability and held-out data likelihood.} } @article{DBLP:journals/ir/WeiCM06, author = {Xing Wei and W. Bruce Croft and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ir/WeiCM06}, doi = {10.1007/s10791-006-9005-5}, journal = {Inf. Retr.}, url = {https://doi.org/10.1007/s10791-006-9005-5}, number = {5}, pages = {589--611}, timestamp = {Sat, 27 May 2017 01:00:00 +0200}, title = {Table extraction for answer retrieval}, volume = {9}, year = {2006}, sum = {Information extraction from tables, using conditional random fields with language and layout features, with application to question answering. Journal paper version of our SIGIR 2003 paper.} } @inproceedings{DBLP:conf/kdd/WangM06, author = {Xuerui Wang and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/WangM06}, booktitle = {Proceedings of the Twelfth {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Philadelphia, PA, USA, August 20-23, 2006}, doi = {10.1145/1150402.1150450}, editor = {Tina Eliassi{-}Rad and Lyle H. Ungar and Mark Craven and Dimitrios Gunopulos}, url = {http://doi.acm.org/10.1145/1150402.1150450}, pages = {424--433}, publisher = {ACM}, timestamp = {Wed, 20 Dec 2006 14:06:10 +0100}, title = {Topics over time: a non-Markov continuous-time model of topical trends}, year = {2006}, sum = {A new LDA-style topic model that models trends over time. The meaning of a topic remains fixed and reliable, but its prevalence over time is captured, and topics may thus focus in on co-occurrence patterns that are time-sensitive. Unlike other work that relies on Markov assumptions or discretization of time, here each topic is associated with a continuous distribution over timestamps. Improvements in topic saliency and the ability to predict time given words.} } @article{DBLP:journals/jair/McCallumWC07, author = {Andrew McCallum and Xuerui Wang and Andr{\'{e}}s Corrada{-}Emmanuel}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/jair/McCallumWC07}, doi = {10.1613/jair.2229}, journal = {J. Artif. Intell. Res.}, url = {https://doi.org/10.1613/jair.2229}, pages = {249--272}, timestamp = {Wed, 21 Jun 2017 01:00:00 +0200}, title = {Topic and Role Discovery in Social Networks with Experiments on Enron and Academic Email}, volume = {30}, year = {2007}, sum = {Journal paper version of IJCAI conference paper on Author-Recipient-Topic (ART) model.} } @inproceedings{DBLP:conf/naacl/CulottaWM07, author = {Aron Culotta and Michael L. Wick and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/CulottaWM07}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Proceedings, April 22-27, 2007, Rochester, New York, {USA}}, editor = {Candace L. Sidner and Tanja Schultz and Matthew Stone and ChengXiang Zhai}, url = {http://www.aclweb.org/anthology/N07-1011}, pages = {81--88}, publisher = {The Association for Computational Linguistics}, timestamp = {Thu, 15 Dec 2016 16:11:53 +0100}, title = {First-Order Probabilistic Models for Coreference Resolution}, year = {2007}, sum = {Traditional coreference uses features only over pairs of mentions. Here we present a conditional random field with first-order logic for expressing features, enabling features over sets of mentions. The result is a new state-of-the-art results on ACE 2004 coref, jumping from 69 to 79---a 45% reduction in error. The advance depends crucially on a new method of parameter estimation for such "weighted logic" models based on learning rankings and error-driven training.} } @inproceedings{DBLP:conf/kdd/CulottaWHMM07, author = {Aron Culotta and Michael L. Wick and Robert Hall and Matthew Marzilli and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/CulottaWHMM07}, booktitle = {Proceedings of the 13th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), San Jose, California, USA, August 12-15, 2007}, doi = {10.1145/1281192.1281217}, editor = {Pavel Berkhin and Rich Caruana and Xindong Wu}, url = {http://doi.acm.org/10.1145/1281192.1281217}, pages = {201--209}, publisher = {ACM}, timestamp = {Fri, 17 Apr 2009 01:00:00 +0200}, title = {Canonicalization of database records using adaptive similarity measures}, year = {2007}, sum = {Defines and explores the problem of "canonicalization"---selecting the best field values for a single, standard record formed from a set of consolodated, co-resolved information sources, such as arise from merging databases, or combining multiple sources of information extraction.} } @inproceedings{DBLP:conf/uai/SuttonM07, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/SuttonM07}, booktitle = {{UAI} 2007, Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), Vancouver, BC, Canada, July 19-22, 2007}, editor = {Ronald Parr and Linda C. van der Gaag}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1712&proceeding_id=23}, pages = {376--383}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 15:02:53 +0200}, title = {Improved Dynamic Schedules for Belief Propagation}, year = {2007}, sum = {Significantly faster inference in graphical models by selecting which BP messages to send based on an approximation to their residual.} } @inproceedings{DBLP:conf/icml/SuttonM07, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/SuttonM07}, booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference ({ICML}), Corvallis, Oregon, USA, June 20-24, 2007}, doi = {10.1145/1273496.1273605}, editor = {Zoubin Ghahramani}, url = {http://doi.acm.org/10.1145/1273496.1273605}, pages = {863--870}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Fri, 01 Jul 2011 12:24:37 +0200}, title = {Piecewise pseudolikelihood for efficient training of conditional random fields}, volume = {227}, year = {2007}, sum = {Train a large CRF in five times faster by dividing it into separate pieces and reducing numbers of predicted variable combinations with pseudolikelihood. Analysis in terms of belief propagation and Bethe energy.} } @article{DBLP:journals/jmlr/SuttonMR07, author = {Charles A. Sutton and Andrew McCallum and Khashayar Rohanimanesh}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/jmlr/SuttonMR07}, journal = {Journal of Machine Learning Research (JMLR)}, url = {http://dl.acm.org/citation.cfm?id=1314523}, pages = {693--723}, timestamp = {Thu, 15 Dec 2011 00:00:00 +0100}, title = {Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data}, volume = {8}, year = {2007}, sum = {Journal paper version of ICML paper by the same authors, with new experiments on marginal likelihood training.} } @inproceedings{DBLP:conf/kdd/MimnoM07, author = {David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/MimnoM07}, booktitle = {Proceedings of the 13th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), San Jose, California, USA, August 12-15, 2007}, doi = {10.1145/1281192.1281247}, editor = {Pavel Berkhin and Rich Caruana and Xindong Wu}, url = {http://doi.acm.org/10.1145/1281192.1281247}, pages = {500--509}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Expertise modeling for matching papers with reviewers}, year = {2007}, sum = {The Author-Persona-Topic model is a LDA-style topic model especially designed to represent expertise as a mixture of topical intersections. We show positive results in matching reviewers to conference papers, as assessed by human judgements.} } @inproceedings{DBLP:conf/jcdl/MimnoM07, author = {David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/jcdl/MimnoM07}, booktitle = {{ACM/IEEE} Joint Conference on Digital Libraries ({JCDL}), Vancouver, BC, Canada, June 18-23, 2007, Proceedings}, doi = {10.1145/1255175.1255196}, editor = {Edie M. Rasmussen and Ray R. Larson and Elaine G. Toms and Shigeo Sugimoto}, url = {http://doi.acm.org/10.1145/1255175.1255196}, pages = {105--106}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Mining a digital library for influential authors}, year = {2007}, sum = {A probabilistic model that ranks authors based on their influence on particular areas of scientific research. Integrates topics with citation patterns.} } @inproceedings{DBLP:conf/jcdl/MimnoM07a, author = {David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/jcdl/MimnoM07a}, booktitle = {{ACM/IEEE} Joint Conference on Digital Libraries ({JCDL}), Vancouver, BC, Canada, June 18-23, 2007, Proceedings}, doi = {10.1145/1255175.1255249}, editor = {Edie M. Rasmussen and Ray R. Larson and Elaine G. Toms and Shigeo Sugimoto}, url = {http://doi.acm.org/10.1145/1255175.1255249}, pages = {376--385}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Organizing the {OCA:} learning faceted subjects from a library of digital books}, year = {2007}, sum = {Introduces the DCM-LDA topic model, which represents topics by a Dirichlet-compound-multinomial rather than a multinomial. In addition to obtaining interesting information about the difference varianes of the topics, this model lends itself to efficient parallelization with very coarse-grained synchronization. The result is a topic model that can run on over 1 billion words in just a few hours.} } @inproceedings{DBLP:conf/icml/MimnoLM07, author = {David M. Mimno and Wei Li and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/MimnoLM07}, booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference ({ICML}), Corvallis, Oregon, USA, June 20-24, 2007}, doi = {10.1145/1273496.1273576}, editor = {Zoubin Ghahramani}, url = {http://doi.acm.org/10.1145/1273496.1273576}, pages = {633--640}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Mixtures of hierarchical topics with Pachinko allocation}, volume = {227}, year = {2007}, sum = {From a large document collection automatically discover topic hierarchies, where documents may be flexibly represented as mixtures across multiple leaves, not just mixtures up and down a single leaf-root path. Thus, for example, we can represent a document about instructing a robot in natural language, where those two topics are leaves. This new model, hPAM, combines the best of pachinko allocation (PAM) and hierarchical LDA (hLDA). Dramatic improvements in held-out data likelihood and mutual information between discovered topics and human-assigned categories} } @inproceedings{DBLP:conf/icdar/HuangLM07, author = {Gary B. Huang and Erik G. Learned{-}Miller and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icdar/HuangLM07}, booktitle = {9th International Conference on Document Analysis and Recognition ({ICDAR}), 23-26 September, Curitiba, Paran{\'{a}}, Brazil}, doi = {10.1109/ICDAR.2007.93}, url = {http://doi.ieeecomputersociety.org/10.1109/ICDAR.2007.93}, pages = {208--212}, publisher = {{IEEE} Computer Society}, timestamp = {Mon, 03 Nov 2014 16:47:52 +0100}, title = {Cryptogram Decoding for {OCR} Using Numerization Strings}, year = {2007}, sum = {Robust OCR without font appearance models by incorporating language modeling.} } @inproceedings{DBLP:conf/naacl/MannM07, author = {Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/MannM07}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Proceedings, April 22-27, 2007, Rochester, New York, {USA}}, editor = {Candace L. Sidner and Tanja Schultz and Matthew Stone and ChengXiang Zhai}, url = {http://www.aclweb.org/anthology/N07-2028}, pages = {109--112}, publisher = {The Association for Computational Linguistics}, timestamp = {Thu, 15 Dec 2016 16:11:53 +0100}, title = {Efficient Computation of Entropy Gradient for Semi-Supervised Conditional Random Fields}, year = {2007}, desc = {Short Paper}, sum = {A new, faster dynamic program for calculating the entropy of a finite-state subsequence and its gradient.} } @inproceedings{DBLP:conf/icml/MannM07, author = {Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/MannM07}, booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference ({ICML}), Corvallis, Oregon, USA, June 20-24, 2007}, doi = {10.1145/1273496.1273571}, editor = {Zoubin Ghahramani}, url = {http://doi.acm.org/10.1145/1273496.1273571}, pages = {593--600}, publisher = {ACM}, series = {{ACM} International Conference Proceeding Series}, timestamp = {Fri, 01 Jul 2011 12:24:37 +0200}, title = {Simple, robust, scalable semi-supervised learning via expectation regularization}, volume = {227}, year = {2007}, sum = {Semi-supervised learning is seldom used in real applications because it is often complicated to implement, fragile in tuning or inefficient for large data. We introduce a new highly usable approach to semi-supervised learning, augmenting traditional label log-likelihood with an additional term that encourages model predictions on unlabeled data to match certain expectations. Positive results on 5 data sets versus EM, transductive SVM, entropy regularization and a graph-based method.} } @inproceedings{DBLP:conf/kdd/DruckPMZ07, author = {Gregory Druck and Chris Pal and Andrew McCallum and Xiaojin Zhu}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/DruckPMZ07}, booktitle = {Proceedings of the 13th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), San Jose, California, USA, August 12-15, 2007}, doi = {10.1145/1281192.1281225}, editor = {Pavel Berkhin and Rich Caruana and Xindong Wu}, url = {http://doi.acm.org/10.1145/1281192.1281225}, pages = {280--289}, publisher = {ACM}, timestamp = {Tue, 12 Jul 2016 01:00:00 +0200}, title = {Semi-supervised classification with hybrid generative/discriminative methods}, year = {2007}, sum = {Leverage unlabeled data for text classification by using an objective function that combines (1) joint probability of labels and words and (2) conditional probability of labels give words.} } @article{DBLP:journals/sigkdd/ZhangYGMSSNM07, author = {Haizheng Zhang and John Yen and C. Lee Giles and Bamshad Mobasher and Myra Spiliopoulou and Jaideep Srivastava and Olfa Nasraoui and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/sigkdd/ZhangYGMSSNM07}, doi = {10.1145/1345448.1345468}, journal = {{SIGKDD} Explorations}, url = {http://doi.acm.org/10.1145/1345448.1345468}, number = {2}, pages = {87--92}, timestamp = {Fri, 18 Apr 2008 01:00:00 +0200}, title = {WebKDD/SNAKDD 2007: web mining and social network analysis post-workshop report}, volume = {9}, year = {2007}, } @inproceedings{DBLP:conf/colt/KananiM07, author = {Pallika H. Kanani and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/colt/KananiM07}, booktitle = {Learning Theory, 20th Annual Conference on Learning Theory ({COLT}), San Diego, CA, USA, June 13-15, 2007, Proceedings}, doi = {10.1007/978-3-540-72927-3_46}, editor = {Nader H. Bshouty and Claudio Gentile}, url = {https://doi.org/10.1007/978-3-540-72927-3_46}, pages = {625--627}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {Fri, 02 Jun 2017 13:01:07 +0200}, title = {Resource-Bounded Information Gathering for Correlation Clustering}, volume = {4539}, year = {2007}, sum = {We present a new class of problems in which the goal is to perform correlational clustering under circumstances in which accuracy can be improved by augmenting the given graph with additional information.} } @inproceedings{DBLP:conf/ijcai/KananiMP07, author = {Pallika H. Kanani and Andrew McCallum and Chris Pal}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ijcai/KananiMP07}, booktitle = {{IJCAI} 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, January 6-12, 2007}, editor = {Manuela M. Veloso}, url = {http://ijcai.org/Proceedings/07/Papers/067.pdf}, pages = {429--434}, timestamp = {Wed, 20 Jul 2016 13:58:40 +0200}, title = {Improving Author Coreference by Resource-Bounded Information Gathering from the Web}, year = {2007}, sum = {Sometimes there is simply insufficient information to make an accurate entity resolution decision, and we must gather additional evidence. This paper describes the use of web queries to improve research paper author coreference, exploring two methods of augmenting a graph partitioning problem: using the web to obtain new features on existing edges, and use the web to obtain new nodes in the graph. We then go on to describe decision-theoretic approaches for maximizing accuracy gain with a limited budget of web queries, and demonstrate our methods on three large data sets} } @inproceedings{DBLP:conf/iccv/JainLM07, author = {Vidit Jain and Erik G. Learned{-}Miller and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/iccv/JainLM07}, booktitle = {{IEEE} 11th International Conference on Computer Vision ({ICCV}), Rio de Janeiro, Brazil, October 14-20, 2007}, doi = {10.1109/ICCV.2007.4409055}, url = {https://doi.org/10.1109/ICCV.2007.4409055}, pages = {1--8}, publisher = {{IEEE} Computer Society}, timestamp = {Wed, 24 May 2017 01:00:00 +0200}, title = {People-LDA: Anchoring Topics to People using Face Recognition}, year = {2007}, sum = {Jointly model people's identity, face appearance in an image, and surrounding text in the image captions with an LDA-style topic model. Improved results in identifying coherent sets of person "mentions"---that is, improved co-reference by using both text and image features.} } @inproceedings{DBLP:conf/uai/LiBM07, author = {Wei Li and David M. Blei and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/LiBM07}, booktitle = {{UAI} 2007, Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), Vancouver, BC, Canada, July 19-22, 2007}, editor = {Ronald Parr and Linda C. van der Gaag}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1696&proceeding_id=23}, pages = {243--250}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 15:02:53 +0200}, title = {Nonparametric Bayes Pachinko Allocation}, year = {2007}, sum = {A version of pachinko allocation that automatically determines the number of topics (and super-topics), and its sparse connectivity structure by Dirichlet process priors. Positive results in redisovering known structure in synthetic data, and in held-out likelihood versus PAM, hLDA and HDP} } @inproceedings{DBLP:conf/icdm/WangMW07, author = {Xuerui Wang and Andrew McCallum and Xing Wei}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icdm/WangMW07}, booktitle = {Proceedings of the 7th {IEEE} International Conference on Data Mining ({ICDM}), October 28-31, 2007, Omaha, Nebraska, {USA}}, doi = {10.1109/ICDM.2007.86}, url = {https://doi.org/10.1109/ICDM.2007.86}, pages = {697--702}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 26 May 2017 01:00:00 +0200}, title = {Topical N-Grams: Phrase and Topic Discovery, with an Application to Information Retrieval}, year = {2007}, sum = {A topic model in the LDA style that uses a Markov model to automatically discover topically-relevant arbitrary-length phrases, not just lists of single words. The phrase discovery is not simply a post-processing step, but an intrinsic part of the model that helps it discover better topics. Experiments on document retrieval tasks.} } @inproceedings{DBLP:conf/kdd/WangPM07, author = {Xuerui Wang and Chris Pal and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/WangPM07}, booktitle = {Proceedings of the 13th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), San Jose, California, USA, August 12-15, 2007}, doi = {10.1145/1281192.1281277}, editor = {Pavel Berkhin and Rich Caruana and Xindong Wu}, url = {http://doi.acm.org/10.1145/1281192.1281277}, pages = {794--803}, publisher = {ACM}, timestamp = {Thu, 23 Aug 2007 09:48:07 +0200}, title = {Generalized component analysis for text with heterogeneous attributes}, year = {2007}, sum = {A topic model based on an undirected graphical model, which makes it easier to incorporate multiple modalities} } @inproceedings{DBLP:conf/uai/MimnoM08, author = {David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/MimnoM08}, booktitle = {{UAI} 2008, Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence (UAI), Helsinki, Finland, July 9-12, 2008}, editor = {David A. McAllester and Petri Myllym{\"{a}}ki}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1318&proceeding_id=24}, pages = {411--418}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 01:00:00 +0200}, title = {Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression}, year = {2008}, sum = {Text documents are usually accompanied by metadata, such as the authors, the publication venue, the date, and any references. Work in topic modeling that has taken such information into account, such as Author-Topic, Citation-Topic, and Topic-over-Time models, has generally focused on constructing specific models that are suited only for one particular type of metadata. This paper presents a simple, unified model for learning topics from documents given arbitrary non-textual features, which can be discrete, categorical, or continuous.} } @inproceedings{DBLP:conf/acl/MannM08, author = {Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/MannM08}, booktitle = {{ACL} 2008, Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL), June 15-20, 2008, Columbus, Ohio, {USA}}, editor = {Kathleen McKeown and Johanna D. Moore and Simone Teufel and James Allan and Sadaoki Furui}, url = {http://www.aclweb.org/anthology/P08-1099}, pages = {870--878}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 04 Mar 2013 20:57:25 +0100}, title = {Generalized Expectation Criteria for Semi-Supervised Learning of Conditional Random Fields}, year = {2008}, sum = {Generalized expectation for semi-supervised learning of linear-chain conditional random fields.} } @inproceedings{DBLP:conf/sigir/DruckMM08, author = {Gregory Druck and Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/sigir/DruckMM08}, booktitle = {Proceedings of the 31st Annual International {ACM} Conference on Research and Development in Information Retrieval ({SIGIR}), Singapore, July 20-24, 2008}, doi = {10.1145/1390334.1390436}, editor = {Sung{-}Hyon Myaeng and Douglas W. Oard and Fabrizio Sebastiani and Tat{-}Seng Chua and Mun{-}Kew Leong}, url = {http://doi.acm.org/10.1145/1390334.1390436}, pages = {595--602}, publisher = {ACM}, timestamp = {Wed, 08 Feb 2017 13:37:23 +0100}, title = {Learning from labeled features using generalized expectation criteria}, year = {2008}, sum = {Learn classifiers by labeling features rather than instances. Extensive evaluation on many text data sets, showing substantial improvement over other methods of semi-supervised learning.} } @inproceedings{DBLP:conf/ntii/WickRMD08, author = {Michael L. Wick and Khashayar Rohanimanesh and Andrew McCallum and AnHai Doan}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ntii/WickRMD08}, booktitle = {Proceedings of the International Workshop on New Trends in Information Integration ({NTII}), Auckland, New Zealand, August 23, 2008}, url = {https://people.cs.umass.edu/~mccallum/papers/mwick08discriminative.pdf}, pages = {16--19}, timestamp = {Fri, 17 Apr 2009 01:00:00 +0200}, title = {A Discriminative Approach to Ontology Mapping}, year = {2008}, sum = {New state-of-the-art results on ontology alignment using graph-shaped conditional random fields, joint inference, and parameter estimation by Rank-Based Training.} } @inproceedings{DBLP:conf/kdd/WickRSM08, author = {Michael L. Wick and Khashayar Rohanimanesh and Karl Schultz and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/WickRSM08}, booktitle = {Proceedings of the 14th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Las Vegas, Nevada, USA, August 24-27, 2008}, doi = {10.1145/1401890.1401977}, editor = {Ying Li and Bing Liu and Sunita Sarawagi}, url = {http://doi.acm.org/10.1145/1401890.1401977}, pages = {722--730}, publisher = {ACM}, timestamp = {Mon, 14 May 2012 09:20:40 +0200}, title = {A unified approach for schema matching, coreference and canonicalization}, year = {2008}, sum = {Information integration, performing joint inference over schema matching, entity resolution and canonicalization, using conditional random fields, features encoding clauses in first-order logic, and efficient inference by Metropolis-Hastings. Positive experimental results on multiple data sets.} } @inproceedings{DBLP:conf/eScience/Reznik-ZellenSTMSAMMT08, author = {Rebecca Reznik{-}Zellen and Bob Stevens and Michael Thorn and Jeff Morse and Mark D. Smucker and James Allan and David M. Mimno and Andrew McCallum and Mark Tuominen}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/eScience/Reznik-ZellenSTMSAMMT08}, booktitle = {Fourth International Conference on e-Science (e-Science), 7-12 December 2008, Indianapolis, IN, {USA}}, doi = {10.1109/eScience.2008.142}, url = {https://doi.org/10.1109/eScience.2008.142}, pages = {382--383}, publisher = {{IEEE} Computer Society}, timestamp = {Fri, 02 Jun 2017 01:00:00 +0200}, title = {InterNano: e-Science for the Nanomanufacturing Community}, year = {2008} } @inproceedings{DBLP:conf/kdd/HallSM08, author = {Robert Hall and Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/HallSM08}, booktitle = {Proceedings of the 14th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Las Vegas, Nevada, USA, August 24-27, 2008}, doi = {10.1145/1401890.1401931}, editor = {Ying Li and Bing Liu and Sunita Sarawagi}, url = {http://doi.acm.org/10.1145/1401890.1401931}, pages = {310--317}, publisher = {ACM}, timestamp = {Mon, 14 May 2012 09:20:40 +0200}, title = {Unsupervised deduplication using cross-field dependencies}, year = {2008}, sum = {Hierarchical Dirichlet process model that jointly clusters citation venue strings based on both string-edit distance and title information.} } @inproceedings{DBLP:conf/conll/McCallum09, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/conll/McCallum09}, booktitle = {Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL), Boulder, Colorado, USA, June 4-5, 2009}, editor = {Suzanne Stevenson and Xavier Carreras}, url = {http://aclweb.org/anthology/W/W09/W09-1101.pdf}, pages = {1}, publisher = {ACL}, timestamp = {Thu, 22 Jan 2015 17:08:32 +0100}, title = {Joint Inference for Natural Language Processing}, year = {2009} } @inproceedings{DBLP:conf/nips/McCallumSS09, author = {Andrew McCallum and Karl Schultz and Sameer Singh}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/McCallumSS09}, booktitle = {Advances in Neural Information Processing Systems (NIPS) 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver, British Columbia, Canada.}, editor = {Yoshua Bengio and Dale Schuurmans and John D. Lafferty and Christopher K. I. Williams and Aron Culotta}, url = {http://papers.nips.cc/paper/3654-factorie-probabilistic-programming-via-imperatively-defined-factor-graphs}, pages = {1249--1257}, publisher = {Curran Associates, Inc.}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {{FACTORIE:} Probabilistic Programming via Imperatively Defined Factor Graphs}, year = {2009} } @article{DBLP:journals/ml/SuttonM09, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ml/SuttonM09}, doi = {10.1007/s10994-009-5112-z}, journal = {Machine Learning (ML)}, url = {https://doi.org/10.1007/s10994-009-5112-z}, number = {2-3}, pages = {165--194}, timestamp = {Sun, 28 May 2017 01:00:00 +0200}, title = {Piecewise training for structured prediction}, volume = {77}, year = {2009} } @inproceedings{DBLP:conf/emnlp/MimnoWNSM09, author = {David M. Mimno and Hanna M. Wallach and Jason Naradowsky and David A. Smith and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/MimnoWNSM09}, booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 6-7 August 2009, Singapore, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D09-1092}, pages = {880--889}, publisher = {ACL}, timestamp = {Wed, 09 Jun 2010 13:47:26 +0200}, title = {Polylingual Topic Models}, year = {2009} } @inproceedings{DBLP:conf/emnlp/DruckSM09, author = {Gregory Druck and Burr Settles and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/DruckSM09}, booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 6-7 August 2009, Singapore, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D09-1009}, pages = {81--90}, publisher = {ACL}, timestamp = {Wed, 09 Jun 2010 13:47:26 +0200}, title = {Active Learning by Labeling Features}, year = {2009} } @inproceedings{DBLP:conf/acl/DruckMM09, author = {Gregory Druck and Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/DruckMM09}, booktitle = {{ACL} 2009, Proceedings of the 47th Annual Meeting of the Association for Computational Linguistics (ACL) and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2-7 August 2009, Singapore}, editor = {Keh{-}Yih Su and Jian Su and Janyce Wiebe}, url = {http://www.aclweb.org/anthology/P09-1041}, pages = {360--368}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 25 Mar 2013 23:10:01 +0100}, title = {Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria}, year = {2009} } @inproceedings{DBLP:conf/nips/WallachMM09, author = {Hanna M. Wallach and David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/WallachMM09}, booktitle = {Advances in Neural Information Processing Systems (NIPS) 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver, British Columbia, Canada.}, editor = {Yoshua Bengio and Dale Schuurmans and John D. Lafferty and Christopher K. I. Williams and Aron Culotta}, url = {http://papers.nips.cc/paper/3854-rethinking-lda-why-priors-matter}, pages = {1973--1981}, publisher = {Curran Associates, Inc.}, timestamp = {Thu, 11 Dec 2014 17:34:07 +0100}, title = {Rethinking {LDA:} Why Priors Matter}, year = {2009} } @inproceedings{DBLP:conf/emnlp/BellareM09, author = {Kedar Bellare and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/BellareM09}, booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 6-7 August 2009, Singapore, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D09-1014}, pages = {131--140}, publisher = {ACL}, timestamp = {Wed, 09 Jun 2010 13:47:26 +0200}, title = {Generalized Expectation Criteria for Bootstrapping Extractors using Record-Text Alignment}, year = {2009} } @inproceedings{DBLP:conf/uai/BellareDM09, author = {Kedar Bellare and Gregory Druck and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/BellareDM09}, booktitle = {{UAI} 2009, Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI), Montreal, QC, Canada, June 18-21, 2009}, editor = {Jeff A. Bilmes and Andrew Y. Ng}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=1652&proceeding_id=25}, pages = {43--50}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 15:02:54 +0200}, title = {Alternating Projections for Learning with Expectation Constraints}, year = {2009} } @inproceedings{DBLP:conf/kdd/YaoMM09, author = {Limin Yao and David M. Mimno and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/YaoMM09}, booktitle = {Proceedings of the 15th {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Paris, France, June 28 - July 1, 2009}, doi = {10.1145/1557019.1557121}, editor = {John F. Elder IV and Fran{\c{c}}oise Fogelman{-}Souli{\'{e}} and Peter A. Flach and Mohammed Javeed Zaki}, url = {http://doi.acm.org/10.1145/1557019.1557121}, pages = {937--946}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Efficient methods for topic model inference on streaming document collections}, year = {2009} } @inproceedings{DBLP:conf/sdm/WickCRM09, author = {Michael L. Wick and Aron Culotta and Khashayar Rohanimanesh and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/sdm/WickCRM09}, booktitle = {Proceedings of the {SIAM} International Conference on Data Mining ({SDM}), April 30 - May 2, 2009, Sparks, Nevada, {USA}}, doi = {10.1137/1.9781611972795.32}, url = {https://doi.org/10.1137/1.9781611972795.32}, pages = {365--376}, publisher = {SIAM}, timestamp = {Wed, 17 May 2017 14:24:53 +0200}, title = {An Entity Based Model for Coreference Resolution}, year = {2009} } @inproceedings{DBLP:conf/nips/WickRSM09, author = {Michael L. Wick and Khashayar Rohanimanesh and Sameer Singh and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/WickRSM09}, booktitle = {Advances in Neural Information Processing Systems (NIPS) 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver, British Columbia, Canada.}, editor = {Yoshua Bengio and Dale Schuurmans and John D. Lafferty and Christopher K. I. Williams and Aron Culotta}, url = {http://papers.nips.cc/paper/3832-training-factor-graphs-with-reinforcement-learning-for-efficient-map-inference}, pages = {2044--2052}, publisher = {Curran Associates, Inc.}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {Training Factor Graphs with Reinforcement Learning for Efficient {MAP} Inference}, year = {2009} } @inproceedings{DBLP:conf/pkdd/SinghSM09, author = {Sameer Singh and Karl Schultz and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/pkdd/SinghSM09}, booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference ({ECML} {PKDD}), Bled, Slovenia, September 7-11, 2009, Proceedings, Part {II}}, doi = {10.1007/978-3-642-04174-7_27}, editor = {Wray L. Buntine and Marko Grobelnik and Dunja Mladenic and John Shawe{-}Taylor}, url = {https://doi.org/10.1007/978-3-642-04174-7_27}, pages = {414--429}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {Mon, 22 May 2017 17:11:17 +0200}, title = {Bi-directional Joint Inference for Entity Resolution and Segmentation Using Imperatively-Defined Factor Graphs}, volume = {5782}, year = {2009} } @article{DBLP:journals/jmlr/MannM10, author = {Gideon S. Mann and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/jmlr/MannM10}, doi = {10.1145/1756006.1756038}, journal = {Journal of Machine Learning Research (JMLR)}, url = {http://doi.acm.org/10.1145/1756006.1756038}, pages = {955--984}, timestamp = {Thu, 22 Apr 2010 01:00:00 +0200}, title = {Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data}, volume = {11}, year = {2010} } @inproceedings{DBLP:conf/icml/DruckM10, author = {Gregory Druck and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/DruckM10}, booktitle = {Proceedings of the 27th International Conference on Machine Learning (ICML), June 21-24, 2010, Haifa, Israel}, editor = {Johannes F{\"{u}}rnkranz and Thorsten Joachims}, url = {http://www.icml2010.org/papers/643.pdf}, pages = {319--326}, publisher = {Omnipress}, timestamp = {Fri, 12 Jun 2015 19:15:11 +0200}, title = {High-Performance Semi-Supervised Learning using Discriminatively Constrained Generative Models}, year = {2010} } @inproceedings{DBLP:conf/emnlp/YaoRM10, author = {Limin Yao and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/YaoRM10}, booktitle = {Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 9-11 October 2010, {MIT} Stata Center, Massachusetts, USA, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D10-1099}, pages = {1013--1023}, publisher = {ACL}, timestamp = {Tue, 18 Jan 2011 09:34:37 +0100}, title = {Collective Cross-Document Relation Extraction Without Labelled Data}, year = {2010} } @article{DBLP:journals/pvldb/WickMM10, author = {Michael L. Wick and Andrew McCallum and Gerome Miklau}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/pvldb/WickMM10}, journal = {PVLDB}, url = {http://www.comp.nus.edu.sg/~vldb2010/proceedings/files/papers/R71.pdf}, number = {1}, pages = {794--804}, timestamp = {Thu, 23 Sep 2010 01:00:00 +0200}, title = {Scalable Probabilistic Databases with Factor Graphs and {MCMC}}, volume = {3}, year = {2010} } @inproceedings{DBLP:conf/pakdd/KananiMH10, author = {Pallika H. Kanani and Andrew McCallum and Shaohan Hu}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/pakdd/KananiMH10}, booktitle = {Advances in Knowledge Discovery and Data Mining, 14th Pacific-Asia Conference ({PAKDD}), Hyderabad, India, June 21-24, 2010. Proceedings. Part {I}}, doi = {10.1007/978-3-642-13657-3_45}, editor = {Mohammed Javeed Zaki and Jeffrey Xu Yu and Balaraman Ravindran and Vikram Pudi}, url = {https://doi.org/10.1007/978-3-642-13657-3_45}, pages = {415--427}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {Thu, 25 May 2017 01:00:00 +0200}, title = {Resource-Bounded Information Extraction: Acquiring Missing Feature Values on Demand}, volume = {6118}, year = {2010} } @inproceedings{DBLP:conf/naacl/SinghYRM10, author = {Sameer Singh and Limin Yao and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/SinghYRM10}, booktitle = {Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics (NLT/NAACL), Proceedings, June 2-4, 2010, Los Angeles, California, {USA}}, url = {http://www.aclweb.org/anthology/N10-1111}, pages = {729--732}, publisher = {The Association for Computational Linguistics}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {Constraint-Driven Rank-Based Learning for Information Extraction}, year = {2010} } @article{DBLP:journals/corr/abs-1005-4298, archiveprefix = {arXiv}, author = {Sameer Singh and Michael L. Wick and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/corr/abs-1005-4298}, eprint = {1005.4298}, journal = {arXiv preprint}, url = {http://arxiv.org/abs/1005.4298}, timestamp = {Wed, 07 Jun 2017 01:00:00 +0200}, title = {Distantly Labeling Data for Large Scale Cross-Document Coreference}, volume = {arXiv:1005.4298}, year = {2010} } @inproceedings{DBLP:conf/uai/RiedelSM10, author = {Sebastian Riedel and David A. Smith and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/RiedelSM10}, booktitle = {{UAI} 2010, Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI), Catalina Island, CA, USA, July 8-11, 2010}, editor = {Peter Gr{\"{u}}nwald and Peter Spirtes}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2143&proceeding_id=26}, pages = {492--499}, publisher = {{AUAI} Press}, timestamp = {Wed, 06 May 2015 15:02:55 +0200}, title = {Inference by Minimizing Size, Divergence, or their Sum}, year = {2010} } @inproceedings{DBLP:conf/pkdd/RiedelYM10, author = {Sebastian Riedel and Limin Yao and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/pkdd/RiedelYM10}, booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference ({ECML} {PKDD}), Barcelona, Spain, September 20-24, 2010, Proceedings, Part {III}}, doi = {10.1007/978-3-642-15939-8_10}, editor = {Jos{\'{e}} L. Balc{\'{a}}zar and Francesco Bonchi and Aristides Gionis and Mich{\`{e}}le Sebag}, url = {https://doi.org/10.1007/978-3-642-15939-8_10}, pages = {148--163}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {Mon, 22 May 2017 17:11:17 +0200}, title = {Modeling Relations and Their Mentions without Labeled Text}, volume = {6323}, year = {2010} } @inproceedings{DBLP:conf/emnlp/MimnoWTLM11, author = {David M. Mimno and Hanna M. Wallach and Edmund M. Talley and Miriam Leenders and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/MimnoWTLM11}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 27-31 July 2011, John McIntyre Conference Centre, Edinburgh, UK, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D11-1024}, pages = {262--272}, publisher = {ACL}, timestamp = {Mon, 21 Nov 2011 12:50:56 +0100}, title = {Optimizing Semantic Coherence in Topic Models}, year = {2011} } @inproceedings{DBLP:conf/cikm/DruckM11, author = {Gregory Druck and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/DruckM11}, booktitle = {Proceedings of the 20th {ACM} Conference on Information and Knowledge Management ({CIKM}), Glasgow, United Kingdom, October 24-28, 2011}, doi = {10.1145/2063576.2063712}, editor = {Craig Macdonald and Iadh Ounis and Ian Ruthven}, url = {http://doi.acm.org/10.1145/2063576.2063712}, pages = {947--956}, publisher = {ACM}, timestamp = {Fri, 11 Nov 2011 19:52:08 +0100}, title = {Toward interactive training and evaluation}, year = {2011} } @inproceedings{DBLP:conf/emnlp/YaoHRM11, author = {Limin Yao and Aria Haghighi and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/YaoHRM11}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 27-31 July 2011, John McIntyre Conference Centre, Edinburgh, UK, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D11-1135}, pages = {1456--1466}, publisher = {ACL}, timestamp = {Mon, 21 Nov 2011 12:50:56 +0100}, title = {Structured Relation Discovery using Generative Models}, year = {2011} } @inproceedings{DBLP:conf/nips/WickM11, author = {Michael L. Wick and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/WickM11}, booktitle = {Advances in Neural Information Processing Systems (NIPS) 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain.}, editor = {John Shawe{-}Taylor and Richard S. Zemel and Peter L. Bartlett and Fernando C. N. Pereira and Kilian Q. Weinberger}, url = {http://papers.nips.cc/paper/4237-query-aware-mcmc}, pages = {2564--2572}, timestamp = {Thu, 11 Dec 2014 17:34:08 +0100}, title = {Query-Aware {MCMC}}, year = {2011} } @inproceedings{DBLP:conf/icml/WickRBCM11, author = {Michael L. Wick and Khashayar Rohanimanesh and Kedar Bellare and Aron Culotta and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/WickRBCM11}, booktitle = {Proceedings of the 28th International Conference on Machine Learning ({ICML}), Bellevue, Washington, USA, June 28 - July 2, 2011}, editor = {Lise Getoor and Tobias Scheffer}, pages = {777--784}, publisher = {Omnipress}, timestamp = {Wed, 29 Mar 2017 16:45:25 +0200}, title = {SampleRank: Training Factor Graphs with Atomic Gradients}, year = {2011} } @inproceedings{DBLP:conf/acl/SinghSPM11, author = {Sameer Singh and Amarnag Subramanya and Fernando C. N. Pereira and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/SinghSPM11}, booktitle = {The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL), Proceedings of the Conference, 19-24 June, 2011, Portland, Oregon, {USA}}, editor = {Dekang Lin and Yuji Matsumoto and Rada Mihalcea}, url = {http://www.aclweb.org/anthology/P11-1080}, pages = {793--803}, publisher = {The Association for Computer Linguistics}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {Large-Scale Cross-Document Coreference Using Distributed Inference and Hierarchical Models}, year = {2011} } @inproceedings{DBLP:conf/emnlp/RiedelM11, author = {Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/RiedelM11}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), 27-31 July 2011, John McIntyre Conference Centre, Edinburgh, UK, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, url = {http://www.aclweb.org/anthology/D11-1001}, pages = {1--12}, publisher = {ACL}, timestamp = {Mon, 21 Nov 2011 12:50:56 +0100}, title = {Fast and Robust Joint Models for Biomedical Event Extraction}, year = {2011} } @inproceedings{DBLP:conf/bionlp/RiedelM11, author = {Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/bionlp/RiedelM11}, booktitle = {Proceedings of BioNLP Shared Task 2011 Workshop, Portland, Oregon, USA, June 24, 2011}, editor = {Jun'ichi Tsujii and Jin{-}Dong Kim and Sampo Pyysalo}, url = {http://aclanthology.info/papers/W11-1807/robust-biomedical-event-extraction-with-dual-decomposition-and-minimal-domain-adaptation}, pages = {46--50}, publisher = {Association for Computational Linguistics}, timestamp = {Thu, 24 Aug 2017 16:30:11 +0200}, title = {Robust Biomedical Event Extraction with Dual Decomposition and Minimal Domain Adaptation}, year = {2011} } @inproceedings{DBLP:conf/bionlp/RiedelMSMM11, author = {Sebastian Riedel and David McClosky and Mihai Surdeanu and Andrew McCallum and Christopher D. Manning}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/bionlp/RiedelMSMM11}, booktitle = {Proceedings of BioNLP Shared Task 2011 Workshop, Portland, Oregon, USA, June 24, 2011}, editor = {Jun'ichi Tsujii and Jin{-}Dong Kim and Sampo Pyysalo}, url = {http://aclanthology.info/papers/W11-1808/model-combination-for-event-extraction-in-bionlp-2011}, pages = {51--55}, publisher = {Association for Computational Linguistics}, timestamp = {Thu, 24 Aug 2017 16:30:11 +0200}, title = {Model Combination for Event Extraction in BioNLP 2011}, year = {2011} } @inproceedings{DBLP:conf/jcdl/BakalovMWM12, author = {Anton Bakalov and Andrew McCallum and Hanna M. Wallach and David M. Mimno}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/jcdl/BakalovMWM12}, booktitle = {Proceedings of the 12th {ACM/IEEE-CS} Joint Conference on Digital Libraries ({JCDL}), Washington, DC, USA, June 10-14, 2012}, doi = {10.1145/2232817.2232861}, editor = {Karim B. Boughida and Barrie Howard and Michael L. Nelson and Herbert Van de Sompel and Ingeborg S{\o}lvberg}, url = {http://doi.acm.org/10.1145/2232817.2232861}, pages = {237--240}, publisher = {ACM}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, title = {Topic models for taxonomies}, year = {2012} } @article{DBLP:journals/corr/abs-1207-4157, archiveprefix = {arXiv}, author = {Ben Wellner and Andrew McCallum and Fuchun Peng and Michael Hay}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/corr/abs-1207-4157}, eprint = {1207.4157}, journal = {arXiv preprint}, url = {http://arxiv.org/abs/1207.4157}, timestamp = {Wed, 07 Jun 2017 01:00:00 +0200}, title = {An Integrated, Conditional Model of Information Extraction and Coreference with Applications to Citation Matching}, volume = {arXiv:1207.4157}, year = {2012} } @article{DBLP:journals/ftml/SuttonM12, author = {Charles A. Sutton and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/ftml/SuttonM12}, doi = {10.1561/2200000013}, journal = {Foundations and Trends in Machine Learning}, url = {https://doi.org/10.1561/2200000013}, number = {4}, pages = {267--373}, timestamp = {Sat, 20 May 2017 01:00:00 +0200}, title = {An Introduction to Conditional Random Fields}, volume = {4}, year = {2012} } @inproceedings{DBLP:conf/nips/BelangerPRM12, author = {David Belanger and Alexandre Passos and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/nips/BelangerPRM12}, booktitle = {Advances in Neural Information Processing Systems (NIPS) 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States.}, editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger}, url = {http://papers.nips.cc/paper/4819-map-inference-in-chains-using-column-generation}, pages = {1853--1861}, timestamp = {Thu, 11 Dec 2014 17:34:07 +0100}, title = {{MAP} Inference in Chains using Column Generation}, year = {2012} } @article{DBLP:journals/bmcbi/McCloskyRSMM12, author = {David McClosky and Sebastian Riedel and Mihai Surdeanu and Andrew McCallum and Christopher D. Manning}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/bmcbi/McCloskyRSMM12}, doi = {10.1186/1471-2105-13-S11-S9}, journal = {{BMC} Bioinformatics}, url = {https://doi.org/10.1186/1471-2105-13-S11-S9}, number = {S-11}, pages = {S9}, timestamp = {Fri, 26 May 2017 01:00:00 +0200}, title = {Combining joint models for biomedical event extraction}, volume = {13}, year = {2012} } @inproceedings{DBLP:conf/acl/YaoRM12, author = {Limin Yao and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/YaoRM12}, booktitle = {The 50th Annual Meeting of the Association for Computational Linguistics (ACL), Proceedings of the Conference, July 8-14, 2012, Jeju Island, Korea - Volume 1: Long Papers}, url = {http://www.aclweb.org/anthology/P12-1075}, pages = {712--720}, publisher = {The Association for Computer Linguistics}, timestamp = {Wed, 15 Aug 2012 08:21:28 +0200}, title = {Unsupervised Relation Discovery with Sense Disambiguation}, year = {2012} } @inproceedings{DBLP:conf/acl/WickSM12, author = {Michael L. Wick and Sameer Singh and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/WickSM12}, booktitle = {The 50th Annual Meeting of the Association for Computational Linguistics (ACL), Proceedings of the Conference, July 8-14, 2012, Jeju Island, Korea - Volume 1: Long Papers}, url = {http://www.aclweb.org/anthology/P12-1040}, pages = {379--388}, publisher = {The Association for Computer Linguistics}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {A Discriminative Hierarchical Model for Fast Coreference at Large Scale}, year = {2012} } @inproceedings{DBLP:conf/wsdm/KananiM12, author = {Pallika H. Kanani and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/wsdm/KananiM12}, booktitle = {Proceedings of the Fifth International Conference on Web Search and Web Data Mining ({WSDM}), Seattle, WA, USA, February 8-12, 2012}, doi = {10.1145/2124295.2124328}, editor = {Eytan Adar and Jaime Teevan and Eugene Agichtein and Yoelle Maarek}, url = {http://doi.acm.org/10.1145/2124295.2124328}, pages = {253--262}, publisher = {ACM}, timestamp = {Tue, 18 Dec 2012 00:00:00 +0100}, title = {Selecting actions for resource-bounded information extraction using reinforcement learning}, year = {2012} } @inproceedings{DBLP:conf/emnlp/SinghWM12, author = {Sameer Singh and Michael L. Wick and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/SinghWM12}, booktitle = {Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), July 12-14, 2012, Jeju Island, Korea}, editor = {Jun'ichi Tsujii and James Henderson and Marius Pasca}, url = {http://www.aclweb.org/anthology/D12-1101}, pages = {1104--1113}, publisher = {ACL}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {Monte Carlo {MCMC:} Efficient Inference by Approximate Sampling}, year = {2012} } @inproceedings{DBLP:conf/emnlp/RiedelSM12, author = {Sebastian Riedel and David A. Smith and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/RiedelSM12}, booktitle = {Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), July 12-14, 2012, Jeju Island, Korea}, editor = {Jun'ichi Tsujii and James Henderson and Marius Pasca}, url = {http://www.aclweb.org/anthology/D12-1067}, pages = {732--743}, publisher = {ACL}, timestamp = {Thu, 22 Jan 2015 16:51:46 +0100}, title = {Parse, Price and Cut--Delayed Column and Row Generation for Graph Based Parsers}, year = {2012} } @inproceedings{DBLP:conf/conll/ZhengVSCM13, author = {Jiaping Zheng and Luke Vilnis and Sameer Singh and Jinho D. Choi and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/conll/ZhengVSCM13}, booktitle = {Proceedings of the Seventeenth Conference on Computational Natural Language Learning (CoNLL), Sofia, Bulgaria, August 8-9, 2013}, editor = {Julia Hockenmaier and Sebastian Riedel}, url = {http://aclweb.org/anthology/W/W13/W13-3517.pdf}, pages = {153--162}, publisher = {ACL}, timestamp = {Wed, 27 Jul 2016 01:00:00 +0200}, title = {Dynamic Knowledge-Base Alignment for Coreference Resolution}, year = {2013} } @inproceedings{DBLP:conf/acl/ChoiM13, author = {Jinho D. Choi and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/ChoiM13}, booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL), 4-9 August 2013, Sofia, Bulgaria, Volume 1: Long Papers}, url = {http://aclweb.org/anthology/P/P13/P13-1104.pdf}, pages = {1052--1062}, publisher = {The Association for Computer Linguistics}, timestamp = {Tue, 26 Nov 2013 16:42:48 +0100}, title = {Transition-based Dependency Parsing with Selectional Branching}, year = {2013} } @inproceedings{DBLP:conf/cikm/YaoRM13, author = {Limin Yao and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/YaoRM13}, booktitle = {Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013}, doi = {10.1145/2509558.2509572}, editor = {Fabian M. Suchanek and Sebastian Riedel and Sameer Singh and Partha Pratim Talukdar}, url = {http://doi.acm.org/10.1145/2509558.2509572}, pages = {79--84}, publisher = {ACM}, timestamp = {Wed, 27 Jul 2016 16:38:54 +0200}, title = {Universal schema for entity type prediction}, year = {2013} } @inproceedings{DBLP:conf/cikm/WickSKM13, author = {Michael L. Wick and Sameer Singh and Ari Kobren and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/WickSKM13}, booktitle = {Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013}, doi = {10.1145/2509558.2509561}, editor = {Fabian M. Suchanek and Sebastian Riedel and Sameer Singh and Partha Pratim Talukdar}, url = {http://doi.acm.org/10.1145/2509558.2509561}, pages = {13--18}, publisher = {ACM}, timestamp = {Wed, 27 Jul 2016 16:38:54 +0200}, title = {Assessing confidence of knowledge base content with an experimental study in entity resolution}, year = {2013} } @inproceedings{DBLP:conf/cikm/WickSPM13, author = {Michael L. Wick and Sameer Singh and Harshal Pandya and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/WickSPM13}, booktitle = {Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013}, doi = {10.1145/2509558.2509570}, editor = {Fabian M. Suchanek and Sebastian Riedel and Sameer Singh and Partha Pratim Talukdar}, url = {http://doi.acm.org/10.1145/2509558.2509570}, pages = {67--72}, publisher = {ACM}, timestamp = {Wed, 27 Jul 2016 16:38:54 +0200}, title = {A joint model for discovering and linking entities}, year = {2013} } @inproceedings{DBLP:conf/tac/SinghYBKAWPPCMM13, author = {Sameer Singh and Limin Yao and David Belanger and Ari Kobren and Sam Anzaroot and Mike Wick and Alexandre Passos and Harshal Pandya and Jinho D. Choi and Brian Martin and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/tac/SinghYBKAWPPCMM13}, booktitle = {Proceedings of the Sixth Text Analysis Conference, ({TAC}), Gaithersburg, Maryland, USA, November 18-19, 2013}, url = {http://www.nist.gov/tac/publications/2013/participant.papers/UMass_IESL.TAC2013.proceedings.pdf}, publisher = {NIST}, timestamp = {Sun, 09 Jul 2017 01:00:00 +0200}, title = {Universal Schema for Slot Filling and Cold Start: UMass {IESL} at {TACKBP} 2013}, year = {2013} } @inproceedings{DBLP:conf/cikm/SinghRMZM13, author = {Sameer Singh and Sebastian Riedel and Brian Martin and Jiaping Zheng and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/cikm/SinghRMZM13}, booktitle = {Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013}, doi = {10.1145/2509558.2509559}, editor = {Fabian M. Suchanek and Sebastian Riedel and Sameer Singh and Partha Pratim Talukdar}, url = {http://doi.acm.org/10.1145/2509558.2509559}, pages = {1--6}, publisher = {ACM}, timestamp = {Wed, 27 Jul 2016 16:38:54 +0200}, title = {Joint inference of entities, relations, and coreference}, year = {2013} } @inproceedings{DBLP:conf/iclr/RiedelYM13, author = {Sebastian Riedel and Limin Yao and Andrew McCallum}, title = {Latent Relation Representations for Universal Schemas}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2013}, url = {http://arxiv.org/abs/1301.4293}, } @inproceedings{DBLP:conf/naacl/RiedelYMM13, author = {Sebastian Riedel and Limin Yao and Andrew McCallum and Benjamin M. Marlin}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/RiedelYMM13}, booktitle = {Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Proceedings, June 9-14, 2013, Westin Peachtree Plaza Hotel, Atlanta, Georgia, {USA}}, editor = {Lucy Vanderwende and Hal Daum{\'{e}} III and Katrin Kirchhoff}, url = {http://aclweb.org/anthology/N/N13/N13-1008.pdf}, pages = {74--84}, publisher = {The Association for Computational Linguistics}, timestamp = {Wed, 05 Apr 2017 12:53:50 +0200}, title = {Relation Extraction with Matrix Factorization and Universal Schemas}, year = {2013} } @inproceedings{DBLP:conf/conll/PassosKM14, author = {Alexandre Passos and Vineet Kumar and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/conll/PassosKM14}, booktitle = {Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL), Baltimore, Maryland, USA, June 26-27, 2014}, editor = {Roser Morante and Wen{-}tau Yih}, url = {http://aclweb.org/anthology/W/W14/W14-1609.pdf}, pages = {78--86}, publisher = {ACL}, timestamp = {Wed, 21 Jan 2015 17:09:07 +0100}, title = {Lexicon Infused Phrase Embeddings for Named Entity Resolution}, year = {2014} } @inproceedings{DBLP:conf/emnlp/NeelakantanSPM14, author = {Arvind Neelakantan and Jeevan Shankar and Alexandre Passos and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/NeelakantanSPM14}, booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), October 25-29, 2014, Doha, Qatar, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, editor = {Alessandro Moschitti and Bo Pang and Walter Daelemans}, url = {http://aclweb.org/anthology/D/D14/D14-1113.pdf}, pages = {1059--1069}, publisher = {ACL}, timestamp = {Sat, 15 Nov 2014 14:12:40 +0100}, title = {Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space}, year = {2014} } @inproceedings{DBLP:conf/uai/BelangerPRM14, author = {David Belanger and Alexandre Passos and Sebastian Riedel and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/BelangerPRM14}, booktitle = {Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence ({UAI}), Quebec City, Quebec, Canada, July 23-27, 2014}, editor = {Nevin L. Zhang and Jin Tian}, url = {https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2441&proceeding_id=30}, pages = {62--71}, publisher = {{AUAI} Press}, timestamp = {Mon, 27 Jul 2015 18:23:18 +0200}, title = {Message Passing for Soft Constraint Dual Decomposition}, year = {2014} } @inproceedings{DBLP:conf/iclr/VilnisM15, author = {Luke Vilnis and Andrew McCallum}, title = {Word Representations via Gaussian Embedding}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2015}, url = {http://arxiv.org/abs/1412.6623}, desc = {Oral Presentation} } @inproceedings{DBLP:conf/acl/AnzarootPBM14, author = {Sam Anzaroot and Alexandre Passos and David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/AnzarootPBM14}, booktitle = {Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics ({ACL}), June 22-27, 2014, Baltimore, MD, USA, Volume 1: Long Papers}, url = {http://aclweb.org/anthology/P/P14/P14-1056.pdf}, pages = {593--602}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 28 Jul 2014 01:00:00 +0200}, title = {Learning Soft Linear Constraints with Application to Citation Field Extraction}, year = {2014} } @inproceedings{DBLP:conf/ictir/McCallum15, author = {Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ictir/McCallum15}, booktitle = {Proceedings of the 2015 International Conference on The Theory of Information Retrieval ({ICTIR}), Northampton, Massachusetts, USA, September 27-30, 2015}, doi = {10.1145/2808194.2808195}, editor = {James Allan and W. Bruce Croft and Arjen P. de Vries and Chengxiang Zhai}, url = {http://doi.acm.org/10.1145/2808194.2808195}, pages = {1}, publisher = {ACM}, timestamp = {Tue, 03 Nov 2015 14:42:32 +0100}, title = {Embedded Representations of Lexical and Knowledge-Base Semantics}, year = {2015} } @inproceedings{DBLP:conf/acl/NeelakantanRM15, author = {Arvind Neelakantan and Benjamin Roth and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/NeelakantanRM15}, booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing ({ACL}), July 26-31, 2015, Beijing, China, Volume 1: Long Papers}, url = {http://aclweb.org/anthology/P/P15/P15-1016.pdf}, pages = {156--166}, publisher = {The Association for Computer Linguistics}, timestamp = {Sun, 02 Aug 2015 19:10:39 +0200}, title = {Compositional Vector Space Models for Knowledge Base Completion}, year = {2015} } @inproceedings{DBLP:conf/acl/StrubellVSM15, author = {Emma Strubell and Luke Vilnis and Kate Silverstein and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/StrubellVSM15}, booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing ({ACL}), July 26-31, 2015, Beijing, China, Volume 1: Long Papers}, url = {http://aclweb.org/anthology/P/P15/P15-1015.pdf}, pages = {146--155}, publisher = {The Association for Computer Linguistics}, timestamp = {Sun, 02 Aug 2015 19:10:39 +0200}, title = {Learning Dynamic Feature Selection for Fast Sequential Prediction}, year = {2015}, desc = {Outstanding Paper Award} } @inproceedings{DBLP:conf/uai/VilnisBSM15, author = {Luke Vilnis and David Belanger and Daniel Sheldon and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/uai/VilnisBSM15}, booktitle = {Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence ({UAI}), July 12-16, 2015, Amsterdam, The Netherlands}, editor = {Marina Meila and Tom Heskes}, pages = {892--901}, publisher = {{AUAI} Press}, timestamp = {Sun, 31 Jan 2016 16:35:16 +0100}, title = {Bethe Projections for Non-Local Inference}, year = {2015} } @article{DBLP:journals/aim/AgarwalABFFKKKL15, author = {Nitin Agarwal and Sean Andrist and Dan Bohus and Fei Fang and Laurie Fenstermacher and Lalana Kagal and Takashi Kido and Christopher Kiekintveld and William F. Lawless and Huan Liu and Andrew McCallum and Hemant Purohit and Oshani Seneviratne and Keiki Takadama and Gavin Taylor}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/aim/AgarwalABFFKKKL15}, journal = {{AI} Magazine}, url = {http://www.aaai.org/ojs/index.php/aimagazine/article/view/2608}, number = {3}, pages = {113--119}, timestamp = {Wed, 14 Oct 2015 01:00:00 +0200}, title = {Reports on the 2015 {AAAI} Spring Symposium Series}, volume = {36}, year = {2015} } @inproceedings{DBLP:conf/iclr/VilnisM15, author = {Arvind Neelakantan and Quoc V. Le and Martin Abadi and Andrew McCallum and Dario Amodei}, title = {Learning a Natural Language Interface with Neural Programmer}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2017}, url = {http://arxiv.org/abs/1611.08945}, } @inproceedings{DBLP:conf/icml/BelangerM16, author = {David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/BelangerM16}, booktitle = {Proceedings of the 33rd International Conference on Machine Learning ({ICML}), New York City, NY, USA, June 19-24, 2016}, editor = {Maria{-}Florina Balcan and Kilian Q. Weinberger}, url = {http://jmlr.org/proceedings/papers/v48/belanger16.html}, pages = {983--992}, publisher = {JMLR.org}, series = {{JMLR} Workshop and Conference Proceedings}, timestamp = {Tue, 12 Jul 2016 21:51:16 +0200}, title = {Structured Prediction Energy Networks}, volume = {48}, year = {2016} } @inproceedings{DBLP:conf/akbc/VergaM16, author = {Patrick Verga and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/akbc/VergaM16}, booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016}, editor = {Jay Pujara and Tim Rockt{\"{a}}schel and Danqi Chen and Sameer Singh}, url = {http://aclweb.org/anthology/W/W16/W16-1312.pdf}, pages = {63--68}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 19 Sep 2016 17:23:19 +0200}, title = {Row-less Universal Schema}, year = {2016}, desc = {Oral Presentation} } @inproceedings{DBLP:conf/naacl/VergaBSRM16, author = {Patrick Verga and David Belanger and Emma Strubell and Benjamin Roth and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/naacl/VergaBSRM16}, booktitle = {{NAACL} {HLT} 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (HLT/NAACL), San Diego California, USA, June 12-17, 2016}, editor = {Kevin Knight and Ani Nenkova and Owen Rambow}, url = {http://aclweb.org/anthology/N/N16/N16-1103.pdf}, pages = {886--896}, publisher = {The Association for Computational Linguistics}, timestamp = {Tue, 13 Sep 2016 19:52:39 +0200}, title = {Multilingual Relation Extraction using Compositional Universal Schema}, year = {2016}, desc = {Oral Presentation}, code = {https://github.com/patverga/torch-relation-extraction}, data = {https://people.cs.umass.edu/~pat/data/naacl-data.tar.gz} } @inproceedings{DBLP:conf/akbc/DasNBM16, author = {Rajarshi Das and Arvind Neelakantan and David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/akbc/DasNBM16}, booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016}, editor = {Jay Pujara and Tim Rockt{\"{a}}schel and Danqi Chen and Sameer Singh}, url = {http://aclweb.org/anthology/W/W16/W16-1304.pdf}, pages = {18--23}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 19 Sep 2016 17:23:19 +0200}, title = {Incorporating Selectional Preferences in Multi-hop Relation Extraction}, year = {2016} } @inproceedings{DBLP:conf/akbc/MartinBNM16, author = {Teresa Martin and Fiete Botschen and Ajay Nagesh and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/akbc/MartinBNM16}, booktitle = {Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016}, editor = {Jay Pujara and Tim Rockt{\"{a}}schel and Danqi Chen and Sameer Singh}, url = {http://aclweb.org/anthology/W/W16/W16-1317.pdf}, pages = {92--96}, publisher = {The Association for Computer Linguistics}, timestamp = {Mon, 19 Sep 2016 17:23:19 +0200}, title = {Call for Discussion: Building a New Standard Dataset for Relation Extraction Tasks}, year = {2016} } @inproceedings{DBLP:conf/recsys/BansalBM16, author = {Trapit Bansal and David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/recsys/BansalBM16}, booktitle = {Proceedings of the 10th {ACM} Conference on Recommender Systems (RecSys), Boston, MA, USA, September 15-19, 2016}, doi = {10.1145/2959100.2959180}, editor = {Shilad Sen and Werner Geyer and Jill Freyne and Pablo Castells}, url = {http://doi.acm.org/10.1145/2959100.2959180}, pages = {107--114}, publisher = {ACM}, timestamp = {Wed, 07 Sep 2016 13:42:11 +0200}, title = {Ask the {GRU}: Multi-task Learning for Deep Text Recommendations}, year = {2016} } @inproceedings{DBLP:conf/tac/Chang16, author = {Haw-Shiuan Chang and Abdurrahman Munir and Ao Liu and Johnny Tian-Zheng Wei and Aaron Traylor and Ajay Nagesh and Nicholas Monath and Patrick Verga and Emma Strubell and Andrew McCallum}, title = {Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema}, booktitle = {Text Analysis Conference, Knowledge Base Population (TAC/KBP)}, year = {2016}, url = {https://pdfs.semanticscholar.org/e53e/b683d8380479a8977d4aef0048e26981cdbe.pdf}, } @inproceedings{DBLP:conf/eacl/McCallumNV17, author = {Patrick Verga and Arvind Neelakantan and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/eacl/McCallumNV17}, booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics ({EACL}), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers}, editor = {Mirella Lapata and Phil Blunsom and Alexander Koller}, url = {http://aclanthology.info/papers/E17-1058/generalizing-to-unseen-entities-and-entity-pairs-with-row-less-universal-schema}, pages = {613--622}, publisher = {Association for Computational Linguistics}, timestamp = {Wed, 09 Aug 2017 16:04:18 +0200}, title = {Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema}, year = {2017}, desc = {Oral Presentation}, data = {https://people.cs.umass.edu/~pat/data/EACL_rowless_entity_types.tar.gz} } @inproceedings{DBLP:conf/eacl/McCallumNDB17, author = {Rajarshi Das and Arvind Neelakantan and David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/eacl/McCallumNDB17}, booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics ({EACL}), Valencia, Spain, April 3-7, 2017, Volume 1: Long Papers}, editor = {Mirella Lapata and Phil Blunsom and Alexander Koller}, url = {http://www.aclweb.org/anthology/E17-1013}, pages = {132--141}, publisher = {Association for Computational Linguistics}, timestamp = {Wed, 09 Aug 2017 16:04:18 +0200}, slides = {http://rajarshd.github.io/talks/Chains_of_Reasoning.pdf}, title = {Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks}, year = {2017} } @inproceedings{DBLP:conf/kdd/KobrenMKM17, author = {Ari Kobren and Nicholas Monath and Akshay Krishnamurthy and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/kdd/KobrenMKM17}, booktitle = {Proceedings of the 23rd {ACM} International Conference on Knowledge Discovery and Data Mining ({SIGKDD}), Halifax, NS, Canada, August 13 - 17, 2017}, doi = {10.1145/3097983.3098079}, url = {http://www.kdd.org/kdd2017/papers/view/an-online-hierarchical-algorithm-for-extreme-clustering}, pages = {255--264}, publisher = {ACM}, timestamp = {Tue, 15 Aug 2017 16:10:36 +0200}, title = {A Hierarchical Algorithm for Extreme Clustering}, year = {2017}, code = {https://github.com/iesl/xcluster}, desc = {Oral Presentation}, video = {http://videolectures.net/kdd2017_kobren_extreme_clustering/} } @inproceedings{DBLP:conf/icml/BelangerYM17, author = {David Belanger and Bishan Yang and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/icml/BelangerYM17}, booktitle = {Proceedings of the 34th International Conference on Machine Learning ({ICML}), Sydney, NSW, Australia, 6-11 August 2017}, editor = {Doina Precup and Yee Whye Teh}, url = {http://proceedings.mlr.press/v70/belanger17a.html}, pages = {429--439}, publisher = {PMLR}, series = {Proceedings of Machine Learning Research}, timestamp = {Wed, 16 Aug 2017 11:08:55 +0200}, title = {End-to-End Learning for Structured Prediction Energy Networks}, volume = {70}, year = {2017} } @inproceedings{DBLP:conf/emnlp/StrubellM17, author = {Emma Strubell and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/StrubellM17}, booktitle = {Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing (SPNLP at EMNLP), Copenhagen, Denmark, September 2017}, editor = {Kai{-}Wei Chang and Ming{-}Wei Chang and Vivek Srikumar and Alexander M. Rush}, url = {http://aclanthology.info/papers/W17-4301/w17-4301}, pages = {1--6}, publisher = {Association for Computational Linguistics}, timestamp = {Mon, 18 Sep 2017 12:23:03 +0200}, title = {Dependency Parsing with Dilated Iterated Graph CNNs}, year = {2017} } @inproceedings{DBLP:conf/emnlp/StrubellVBM17, author = {Emma Strubell and Patrick Verga and David Belanger and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/emnlp/StrubellVBM17}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing ({EMNLP}), Copenhagen, Denmark, September 9-11, 2017}, editor = {Martha Palmer and Rebecca Hwa and Sebastian Riedel}, url = {https://arxiv.org/abs/1702.02098}, pages = {2660--2670}, publisher = {Association for Computational Linguistics}, timestamp = {Fri, 15 Sep 2017 17:29:53 +0200}, title = {Fast and Accurate Entity Recognition with Iterated Dilated Convolutions}, year = {2017}, code = {https://github.com/iesl/dilated-cnn-ner} } @inproceedings{DBLP:conf/nips/ChangLM17, author = {Haw{-}Shiuan Chang and Erik G. Learned{-}Miller and Andrew McCallum}, title = {Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples}, booktitle = {Advances in Neural Information Processing Systems (NIPS)}, year = {2017}, poster = {http://people.umass.edu/hawshiuancha/NIPS_poster_active_bias.pdf}, url = {http://arxiv.org/abs/1704.07433}, } @inproceedings{chang2017unsupervised, title={Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection}, author={Haw-Shiuan Chang and ZiYun Wang and Luke Vilnis and Andrew McCallum}, booktitle={Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL)}, url = {http://arxiv.org/abs/1710.00880}, year = {2018}, code = {https://github.com/iesl/Distributional-Inclusion-Vector-Embedding}, poster = {http://docs.wixstatic.com/ugd/e150d8_925731e34b974de881cbe54f66807d36.pdf}, demo = {https://bl.ocks.org/chsu5358/raw/f08d4755b0f04e113c139a72a977df5c/} } @inproceedings{DBLP:conf/semeval/AugensteinDRVM17, author = {Isabelle Augenstein and Mrinal Das and Sebastian Riedel and Lakshmi Vikraman and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/semeval/AugensteinDRVM17}, booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval at ACL), Vancouver, Canada, August 3-4, 2017}, doi = {10.18653/v1/S17-2091}, editor = {Steven Bethard and Marine Carpuat and Marianna Apidianaki and Saif M. Mohammad and Daniel M. Cer and David Jurgens}, url = {http://www.aclweb.org/anthology/S17-2091}, pages = {546--555}, publisher = {Association for Computational Linguistics}, timestamp = {Wed, 16 Aug 2017 01:00:00 +0200}, title = {SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications}, year = {2017} } @inproceedings{DBLP:conf/acl/DasZRM17, author = {Rajarshi Das and Manzil Zaheer and Siva Reddy and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/acl/DasZRM17}, booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics ({ACL}), Vancouver, Canada, July 30 - August 4, Volume 2: Short Papers}, doi = {10.18653/v1/P17-2057}, editor = {Regina Barzilay and Min{-}Yen Kan}, url = {https://doi.org/10.18653/v1/P17-2057}, pages = {358--365}, publisher = {Association for Computational Linguistics}, timestamp = {Fri, 04 Aug 2017 16:38:24 +0200}, title = {Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks}, year = {2017} } @article{DBLP:journals/corr/BansalNM17, archiveprefix = {arXiv}, author = {Trapit Bansal and Arvind Neelakantan and Andrew McCallum}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/journals/corr/BansalNM17}, eprint = {1706.07179}, journal = {arXiv preprint}, url = {http://arxiv.org/abs/1706.07179}, timestamp = {Mon, 03 Jul 2017 01:00:00 +0200}, title = {RelNet: End-to-end Modeling of Entities {\&} Relations}, volume = {arXiv:1706.07179}, year = {2017} } @inproceedings{DBLP:conf/icml_ws/Thai17, author = {Dung Thai and Shikhar Murty and Trapit Bansal and Luke Vilnis and David Belanger and Andrew McCallum}, title = {Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling}, booktitle = {International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS)}, year = {2017}, url = {http://arxiv.org/abs/1708.00553}, } @inproceedings{DBLP:conf/icml_ws/Li17, author = {Xiang Li and Luke Vilnis and Andrew McCallum}, title = {Improved Representation Learning for Predicting Commonsense Ontologies}, booktitle = {International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS)}, year = {2017}, url = {http://arxiv.org/abs/1708.00549}, } @inproceedings{DBLP:conf/tac/Benjamin15, author = {Benjamin Roth and Nicholas Monath and David Belanger and Emma Strubell and Patrick Verga and Andrew McCallum}, title = {Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches}, booktitle = {Text Analysis Conference, Knowledge Base Population (TAC/KBP)}, year = {2015}, url = {https://tac.nist.gov/publications/2015/participant.papers/TAC2015.UMass_IESL.proceedings.pdf}, } @inproceedings{DBLP:conf/tac/Benjamin14, author = {Benjamin Roth and Emma Strubell and John Sullivan and Lakshmi Vikraman and Katherine Silverstein and and Andrew McCallum}, title = {Universal Schema for Slot-Filling, Cold-Start KBP and Event Argument Extraction: UMass IESL at TAC KBP 2014}, booktitle = {Text Analysis Conference, Knowledge Base Population (TAC/KBP)}, year = {2014}, url = {https://pdfs.semanticscholar.org/e53e/b683d8380479a8977d4aef0048e26981cdbe.pdf}, } @inproceedings{DBLP:conf/aaai-ss/Neelakantan15, author = {Arvind Neelakantan and Benjamin Roth and Andrew McCallum}, title = {Compositional Vector Space Models for Knowledge Base Inference}, booktitle = {AAAI Spring Symposium Series (AAAI-SS)}, year = {2015}, url = {https://www.aaai.org/ocs/index.php/SSS/SSS15/paper/viewFile/10254/10032}, } @inproceedings{DBLP:conf/aaai-ss/Benjamin14, author = {Evgeniy Gabrilovich and Ramanathan Guha and Andrew McCallum and Kevin Murphy}, title = {Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches}, booktitle = {AAAI Spring Symposium Series (AAAI-SS)}, year = {2015}, url = {http://www.aaai.org/Press/Reports/Symposia/Spring/ss-15-03.php}, } @inproceedings{DBLP:conf/NIPS-WS/Strubell14, author = {Emma Strubell and Luke Vilnis and and Andrew McCallum}, title = {Training for Fast Sequential Prediction Using Dynamic Feature Selection}, booktitle = {NIPS Workshop on Modern Machine Learning and NLP (NIPS WS)}, year = {2014}, url = {http://arxiv.org/abs/1410.8498}, } @inproceedings{DBLP:conf/akbc/NeelakantanRM14, author = {Arvind Neelakantan and Benjamin Roth and Andrew McCallum}, title = {Knowledge Base Completion using Compositional Vector Space Models}, booktitle = {4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS}, year = {2014}, url = {https://people.cs.umass.edu/~arvind/akbc.pdf}, desc = {Outstanding Paper Award} } @inproceedings{DBLP:conf/akbc/Benjamin14, author = {Benjamin Roth and Emma Strubell and Katherine Silverstein and Andrew McCallum}, title = {Minimally Supervised Event Argument Extraction using Universal Schema}, booktitle = {4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS}, year = {2014}, url = {http://www.akbc.ws/2014/submissions/akbc2014_submission_26.pdf}, } @inproceedings{DBLP:conf/akbc/NeelakantanPM14, author = {Arvind Neelakantan and Alexandre Passos and Andrew McCallum}, title = {A Hierarchical Model for Universal Schema Relation Extraction}, booktitle = {4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS}, year = {2014}, url = {https://people.cs.umass.edu/~arvind/akbc-hierarchical.pdf}, } @inproceedings{DBLP:conf/peer/Soergel13, author = {David Soergel and Adam Saunders and Andrew McCallum}, title = {Open Scholarship and Peer Review: a Time for Experimentation}, booktitle = {ICML Workshop on Peer Reviewing and Publishing Models (PEER)}, year = {2013}, url = {https://works.bepress.com/andrew_mccallum/52/}, } @inproceedings{DBLP:conf/peer/Anzaroot13, author = {Sam Anzaroot and Andrew McCallum}, title = {A New Dataset for Fine-Grained Citation Field Extraction}, booktitle = {ICML Workshop on Peer Reviewing and Publishing Models (PEER)}, year = {2013}, url = {https://openreview.net/pdf?id=ffO1Piqs1KZo5}, } @inproceedings{DBLP:conf/peer/Soergel13, author = {Michael L Wick and Ari Kobren and Andrew McCallum}, title = {Large-scale Author Coreference via Hierarchical Entity Representations}, booktitle = {ICML Workshop on Peer Reviewing and Publishing Models (PEER)}, year = {2013}, url = {https://openreview.net/pdf?id=TTFCKqmXtgaYf}, } @article{DBLP:journals/umass/Soergel13, author = {Sameer Singh and Amar Subramanya and Fernando Pereira and Andrew McCallum}, title = {Wikilinks: A Large-scale Cross-Document Coreference Corpus Labeled via Links to Wikipedia}, journal = {Technical Report (TR) UMASS-CS-2012-015, October, 2012}, year = {2013}, url = {https://web.cs.umass.edu/publication/docs/2012/UM-CS-2012-015.pdf}, } @inproceedings{DBLP:conf/nips_ws/Soergel13, author = {Alexandre Passos and Luke Vilnis and Andrew McCallum}, title = {Optimization and Learning in FACTORIE}, booktitle = {Neural Information Processing Systems Workshop on Optimization for Machine Learning (NIPS WS)}, year = {2013}, url = {http://people.cs.umass.edu/~luke/nips-ws-factorie-optimization.pdf}, } @inproceedings{DBLP:conf/nips_ws/Belanger13, author = {David Belanger and Dan Sheldon and Andrew McCallum}, title = {Marginal Inference in MRFs using Frank-Wolfe}, booktitle = {Neural Information Processing Systems Workshop on Greedy Optimization, Frank-Wolfe and Friends (NIPS WS)}, year = {2013}, url = {https://people.cs.umass.edu/~belanger/Belanger_Frank_Wolfe_MRF.pdf}, } @inproceedings{DBLP:conf/nips_ws/Singh13, author = {Sameer Singh and Sebastian Riedel and Andrew McCallum}, title = {Anytime Belief Propagation Using Sparse Domains}, booktitle = {Neural Information Processing Systems Workshop on Resource-Efficient Machine Learning (NIPS WS)}, year = {2013}, url = {https://arxiv.org/pdf/1311.3368v1.pdf}, } @inproceedings{DBLP:conf/icml_ws/Belanger12, author = {David Belanger and Alexandre Passos and Sebastian Riedel and Andrew McCallum}, title = {Speeding up MAP with Column Generation and Block Regularization}, booktitle = {ICML Workshop on Inferning: Interactions between Inference and Learning (ICML WS)}, year = {2012}, url = {http://www.riedelcastro.org/publications/papers/belanger12speeding.pdf}, } @inproceedings{DBLP:conf/akbc/Wick12, author = {Michael Wick and Karl Schultz and and Andrew McCallum}, title = {Human Machine Cooperation with Epistemological DBs: Supporting User Corrections to Automatically Constructed KBs}, booktitle = {NAACL Workshop on Automatic Knowledge Base Construction (AKBC)}, year = {2012}, url = {https://akbcwekex2012.files.wordpress.com/2012/05/26_paper.pdf}, desc = {Best paper runner-up} } @inproceedings{DBLP:conf/akbc/Singh12, author = {Sameer Singh and Michael Wick and and Andrew McCallum}, title = {Monte Carlo MCMC: Efficient Inference by Sampling Factors}, booktitle = {NAACL Workshop on Automatic Knowledge Base Construction (AKBC)}, year = {2012}, url = {http://people.cs.umass.edu/~mwick/MikeWeb/Publications_files//singh12mcmcmc.pdf}, } @inproceedings{DBLP:conf/nips_ws/Passos11, author = {Alexandre Passos and Hanna Wallach and Andrew McCallum}, title = {Correlations and anticorrelations in LDA inference}, booktitle = {Neural Information Processing Systems Workshop on Challenges in Learning Hierarchical Models: Transfer Learning and Optimization (NIPS WS)}, year = {2011}, url = {http://www.ic.unicamp.br/~tachard/docs/corrlda.pdf}, } @inproceedings{DBLP:conf/nips_ws/SinghMM11, author = {Sameer Singh and Brian Martin and Andrew McCallum}, title = {Inducing Value Sparsity for Parallel Inference in Tree-shaped Models}, booktitle = {Neural Information Processing Systems Workshop on Computational Trade-offs in Statistical Learning (NIPS WS)}, year = {2011}, url = {https://pdfs.semanticscholar.org/5439/70769b245e03917ef80703c7a741b5a63d9e.pdf}, } @inproceedings{DBLP:conf/nips_ws/SinghM11, author = {Sameer Singh and Andrew McCallum}, title = {Towards Asynchronous Distributed MCMC Inference for Large Graphical Models}, booktitle = {Neural Information Processing Systems Workshop on Algorithms, Systems, and Tools for Learning at Scale (NIPS WS)}, year = {2011}, url = {https://pdfs.semanticscholar.org/8ec0/ef13749780d7baac0aff13a81e3ff4d86787.pdf}, } @inproceedings{DBLP:conf/MIND/Klinger11, author = {Roman Klinger and Sebastian Riedel and Andrew McCallum}, title = {Inter-Event Dependencies support Event Extraction from Biomedical Literature}, booktitle = {Mining Complex Entities from Network and Biomedical Data (MIND), Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)}, year = {2011}, url = {http://www.riedelcastro.org/publications/papers/klinger11interevent.pdf}, } @article{DBLP:journals/nature_method/Talley11, author = {Edmund M Talley and David Newman and David Mimno and Bruce W Herr II and Hanna M Wallach and Gully Burns and Miriam Leenders and Andrew McCallum}, title = {Database of NIH grants using machine-learned categories and graphical clustering}, journal = {Nature Methods, 8, 443–444, 27 May 2011}, year = {2011}, url = {http://www.nature.com/nmeth/journal/v8/n6/full/nmeth.1619.html}, } @inproceedings{DBLP:conf/FnT_ML/Sutton10, author = {Charles Sutton and Andrew McCallum}, title = {An Introduction to Conditional Random Fields}, booktitle = {Foundations and Trends in Machine Learning (FnT ML)}, year = {2010}, url = {https://arxiv.org/pdf/1011.4088v1.pdf}, } @article{Singh2010Distantly, title={Distantly labeling data for large scale cross-document coreference}, author={Sameer Singh and Michael Wick and Andrew McCallum}, journal={arXiv preprint}, url = {https://arxiv.org/pdf/1005.4298.pdf}, eprint = {1005.4298}, volume = {arXiv:1005.4298}, year={2010} } @inproceedings{DBLP:conf/nips_ws/Singh10, author = {Sameer Singh and Amarnag Subramanya and Fernando Pereira and Andrew McCallum}, title = {Distributed MAP Inference for Undirected Graphical Models}, booktitle = {Neural Information Processing Systems Workshop on Learning on Cores, Clusters, and Clouds (NIPS WS)}, year = {2010}, url = {https://pdfs.semanticscholar.org/d9b9/7684960aad2fefb39d880f0974a7fc8318e8.pdf}, } @inproceedings{DBLP:conf/AMTA/Roth10, author = {Benjamin Roth and Andrew McCallum and Marc Dymetman and Nicola Cancedda}, title = {Machine Translation Using Overlapping Alignments and SampleRank}, booktitle = {Proceedings of the Ninth Conference of the Association for Machine Translation in the Americas (AMTA)}, year = {2010}, url = {http://www.mt-archive.info/AMTA-2010-Roth.pdf}, } @inproceedings{DBLP:conf/nips_ws/Wick09, author = {Michael Wick and Khashayar Rohanimanesh and Aron Culotta and Andrew McCallum}, title = {SampleRank: Learning Preferences from Atomic Gradients}, booktitle = {Neural Information Processing Systems Workshop on Advances in Ranking (NIPS WS)}, year = {2009}, url = {https://people.cs.umass.edu/~mwick/MikeWeb/Publications_files/wick09samplerank.pdf}, } @article{DBLP:journals/umass/Rohanimanesh09, author = {Khashayar Rohanimanesh and Michael Wick and Andrew McCallum}, title = {Inference and Learning in Large Factor Graphs with Adaptive Proposal Distributions}, journal = {University of Massachusetts Technical Report #UM-CS-2009-008 (TR)}, year = {2009}, url = {https://ciir-publications.cs.umass.edu/getpdf.php?id=888}, } @article{DBLP:journals/umass/Wick09, author = {Michael Wick and Andrew McCallum}, title = {Advances in Learning and Inference for Partition-wise Models of Coreference Resolution}, journal = {University of Massachusets Technical Report # UM-CS-2009-028 (TR)}, year = {2009}, url = {https://people.cs.umass.edu/~mwick/MikeWeb/Publications_files/wick09advances.pdf}, } @article{DBLP:journals/master_thesis/Wick09, author = {Michael Wick}, title = {Representing Uncertainty in Databases with Scalable Factor Graphs}, journal = {Masters Thesis/Synthesis. Readers: Andrew McCallum and Gerome Miklau}, year = {2009}, url = {https://people.cs.umass.edu/~mwick/MikeWeb/Publications_files/wick09representing.pdf}, } @article{DBLP:journals/umass/Kanani09, author = {Pallika Kanani and Andrew McCallum and Ramesh Sitaraman}, title = {Towards Theoretical Bounds for Resource-bounded Information Gathering for Correlation Clustering}, journal = {UMass TechReport UM-CS-2009-027 (TR)}, year = {2009}, url = {https://people.cs.umass.edu/~pallika/publications/synthesis_pallika.pdf}, } @article{DBLP:journals/umass/Rohanimanesh09, author = {Khashayar Rohanimanesh and Michael Wick and Sameer Singh and and Andrew McCallum}, title = {MAP inference in Large Factor Graphs with Reinforcement Learning}, journal = {UMass Technical Report #UM-CS-2008-040 (TR)}, year = {2009}, url = {https://web.cs.umass.edu/publication/docs/2008/UM-CS-2008-040.pdf}, } @inproceedings{DBLP:conf/nips_ws/Mimno08, author = {David Mimno and Hanna Wallach and Andrew McCallum}, title = {Gibbs Sampling for Logistic Normal Topic Models with Graph-Based Priors}, booktitle = {NIPS Workshop on Analyzing Graphs (NIPS WS), 2008, Whistler, BC.}, year = {2008}, url = {https://mimno.infosci.cornell.edu/papers/sampledlgstnorm.pdf}, } @inproceedings{DBLP:conf/nips_ws/McCallum08, author = {Andrew McCallum and Khashayar Rohanemanesh and Michael Wick and Karl Schultz and Sameer Singh}, title = {FACTORIE: Efficient Probabilistic Programming for Relational Factor Graphs via Imperative Declarations of Structure, Inference and Learning}, booktitle = {NIPS Workshop on Probabilistic Programming (NIPS WS)}, year = {2008}, url = {https://people.cs.umass.edu/~mccallum/papers/factorie-nipsws.pdf}, sum = {Discriminatively trained undirected graphical models, or conditional random fields, have had wide empirical success, and there has been increasing interest in toolkits that ease their application to complex relational data. Although there has been much historic interest in the combination of logic and probability, we argue that in this mixture 'logic' is largely a red herring. The power in relational models is in their repeated structure and tied parameters; and logic is not necessarily the best way to define these structures. Rather than using a declarative language, such as SQL or first-order logic, we advocate using an object-oriented imperative language to express various aspects of model structure, inference and learning. By combining the traditional, declarative, statistical semantics of factor graphs with imperative definitions of their construction and operation, we allow the user to mix declarative and procedural domain knowledge, and also gain significant efficiencies. We have implemented our ideas in a system we call FACTORIE, a software library for an object-oriented, strongly-typed, functional JVM language named Scala.} } @inproceedings{DBLP:conf/ntii/WickRMD08, author = {Michael L. Wick and Khashayar Rohanimanesh and Andrew McCallum and AnHai Doan}, bibsource = {dblp computer science bibliography, http://dblp.org}, biburl = {http://dblp.org/rec/bib/conf/ntii/WickRMD08}, booktitle = {Proceedings of the International Workshop on New Trends in Information Integration ({NTII} 2008), Auckland, New Zealand, August 23, 2008}, url = {https://people.cs.umass.edu/~mccallum/papers/mwick08discriminative.pdf}, pages = {16--19}, timestamp = {Fri, 17 Apr 2009 01:00:00 +0200}, title = {A Discriminative Approach to Ontology Mapping}, year = {2008}, sum = {New state-of-the-art results on ontology alignment using graph-shaped conditional random fields, joint inference, and parameter estimation by Rank-Based Training.} } @inproceedings{DBLP:conf/icml_ws/Wallach08, author = {Hanna Wallach and Charles Sutton and Andrew McCallum}, title = {Bayesian Modeling of Dependency Trees Using Hierarchical Pitman-Yor Priors}, booktitle = {International Conference on Machine Learning, Workshop on Prior Knowledge for Text and Language Processing (ICML WS)}, year = {2008}, url = {https://people.cs.umass.edu/~mccallum/papers/dp3ws08.pdf}, sum = {Two Bayesian dependency parsing models: 1. Model with Pitman-Yor prior that significantly improves Eisner's classic model; 2. Latent-variable model that learns "syntactic" topics.}, } @inproceedings{DBLP:conf/aaai_ws/Druck08, author = {Gregory Druck and Gerome Miklau and Andrew McCallum}, title = {Learning to Predict the Quality of Contributions to Wikipedia}, booktitle = {AAAI Workshop on Wikipedia and AI (AAAI WS)}, year = {2008}, url = {https://people.cs.umass.edu/~mccallum/papers/druck08wikiai.pdf}, sum = {Predict the longevity of an edit to Wikipedia, using textual features of the edit as well as features of the editor. Could be part of a tool to prioritize verification of changes to Wikipedia.}, } @article{DBLP:journals/MLJ/Sutton08, author = {Charles Sutton and Andrew McCallum}, title = {Piecewise Training for Structured Prediction}, journal = {Machine Learning Journal (MLJ)}, year = {2008}, url = {https://people.cs.umass.edu/~mccallum/papers/pw08mljs.pdf}, sum = {Efficiently train CRFs in parts. It works well even though full joint inference is used at test time.}, } @article{DBLP:journals/JMLR_submission/Li08, author = {Wei Li and Andrew McCallum}, title = {Pachinko Allocation: Scalable Mixture Models of Topic Correlations}, journal = {Submitted to the Journal of Machine Learning Research (JMLR)}, year = {2008}, url = {https://people.cs.umass.edu/~mccallum/papers/pam08jmlrs.pdf}, sum = {The pachinko allocation model represents nested correlations among topics using a DAG. This paper has work is in efficiently fitting these models, (as well as plain old LDA) by creating and leveraging sparsity in the distribution over topics to be sampled for each document.}, } @article{DBLP:journals/umass/Hall07, author = {Robert Hall and Charles Sutton and Andrew McCallum}, title = {Unsupervised Coreference of Publication Venues}, journal = {University of Massachusetts Amherst Technical Report (TR)}, year = {2007}, url = {https://pdfs.semanticscholar.org/cb79/a9fe3226f27784b60a0d2ea5abb5a9e5f396.pdf}, sum = {A generative non-parametric mixture model for entity resolution of publication venues that leverages both the venue titles as well as distributions over words in paper titles.}, } @article{DBLP:journals/umass/McCallum07, author = {Andrew McCallum and Gideon Mann and Gregory Druck}, title = {Generalized Expectation Criteria}, journal = {University of Massachusetts Amherst Technical Report #2007-60 (TR)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/ge08note.pdf}, sum = {This note introduces and motivates Generalized Expectation (GE) criteria. GE criteria are terms in a parameter-estimation objective function that express preferences about model expectations. In certain simple cases, GE falls into the same equivalence class as moment matching, maximum likelihood and maximum entropy estimation. However, our work focusses on leveraging GE's special flexibility in three non-traditional ways: (1) GE criteria can be specified indepently of the model parameterization. In factor graphs, we break the traditional one-to-one mapping between (a) subsets of variables participating in parametered model factors and (b) subsets of variables over which the objective function's expectations are calculated. (2) Within the same objective function, multiple GE terms that are conditional expectations can be conditioned on multiple different data sets. This is useful for semi-supervised learning and transfer learning. (3) A target expectation (or more generally the expectation preference function can come from any source, including other tasks or human domain knowledge. GE is the successor to Expectation Regularization, which is described in our ICML 2007 paper.}, } @article{DBLP:journals/umass/Druck07, author = {Gregory Druck and Gideon Mann and Andrew McCallum}, title = {Reducing Annotation Effort using Generalized Expectation Criteria--DRAFT}, journal = {University of Massachusetts Amherst Technical Report #2007-62 (TR)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/druck07reducing.pdf}, sum = {A version of Generalized Expectation (GE) in which the supervision is provided by labeling features instead of instances. Dramatically faster wall-clock labeling to acheive high accuracy. Experiments on document classification.}, } @inproceedings{DBLP:conf/nips_ws/Mimno07, author = {David Mimno and Hanna M. Wallach and Andrew McCallum}, title = {Community-based Link Prediction with Text}, booktitle = {NIPS Workshop on Statistical Network Modeling (NIPS WS)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/mimno2007nipsws.pdf}, sum = {New state-of-the-art results in link-prediction using a latent-variable topic model, in which "community" variables are associated with topic distributions and author distributions. Thus the model combines the use of language/topics and co-authorships to discover communities.}, } @inproceedings{DBLP:conf/nips_ws/Druck07, author = {Gregory Druck and Gideon Mann and Andrew McCallum}, title = {Leveraging Existing Resources using Generalized Expectation Criteria}, booktitle = {NIPS Workshop on Learning Problem Design (NIPS WS)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/druck07leveraging.pdf}, sum = {Generalized Expectation applied in situations in which there is no labeled data. All supervision is obtained form existing auxiliary resources such as lexicons. Experiments on information extraction.}, } @inproceedings{DBLP:conf/nips_ws/Bellare07, author = {Kedar Bellare and Partha Pratim Talukdar and Giridhar Kumaran and Fernando Pereira and Mark Liberman and Andrew McCallum and Mark Dredze}, title = {Lightly-Supervised Attribute Extraction for Web Search}, booktitle = {NIPS Workshop on Machine Learning for Web Search (NIPS WS)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/attr_extr_nipsws.pdf}, sum = {Extract a large number of attributes of different entities from natural language text. Methods based on co-training and maximum entropy classifiers.}, } @article{DBLP:journals/book/McCallum07, author = {Andrew McCallum and Xuerui Wang and Natasha Mohanty}, title = {Joint Group and Topic Discovery from Relations and Text}, journal = {Statistical Network Analysis: Models, Issues and New Directions, Lecture Notes in Computer Science 4503, pp. 28-44 (Book chapter), 2007}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/gt-bookch07.pdf}, sum = {Book chapter version of NIPS 2006 conference paper. Social network analysis that simultaneously discovers groups of entities and also clusters attributes of their relations, such that clustering in each dimension in forms the other. Applied to the voting records and corresponding text of resolutions from the U.S. Senate and the U.N., showing that incorporating the votes results in more salient topic clusters, and that different groupings of legislators emerge from different topics.}, } @inproceedings{DBLP:conf/IIWeb/Bellare07, author = {Kedar Bellare and Andrew McCallum}, title = {Learning Extractors from Unlabeled Text using Relevant Databases}, booktitle = {Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/bellare-iiweb07.pdf}, sum = {Use conditional random fields to learn information extractors both from DB fields and from alignments of DB in free text. Uses an Alignment CRF, similar to our UAI 2005 paper.}, } @inproceedings{DBLP:conf/IIWeb/Kanani07, author = {Pallika Kanani and Andrew McCallum}, title = {Efficient Strategies for Improving Partitioning-Based Author Coreference by Incorporating Web Pages as Graph Nodes}, booktitle = {Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/kanani-iiweb07.pdf}, sum = {Improve entity resolution by adding web pages as new "mentions" to the graph-partitioning problem, and do so efficiently by selecting a subset of the possible queries and a subset of the returned pages.}, } @inproceedings{DBLP:conf/IIWeb/Mimno07, author = {David Mimno and Andrew McCallum}, title = {Probabilistic Representations for Integrating Unreliable Data Sources}, booktitle = {Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/mimno-iiweb07.pdf}, sum = {Probabilistic representation of field values used in merging and augmenting information from DBPL and research paper PDFs.}, } @inproceedings{DBLP:conf/IIWeb/Culotta07, author = {Aron Culotta and Pallika Kanani and Robert Hall and Michael Wick and and Andrew McCallum}, title = {Author Disambiguation using Error-Driven Machine Learning With a Ranking Loss Function}, booktitle = {Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/culotta07author.pdf}, sum = {Entity resolution of people using high-order features, made efficient with Metropolis-Hastings and SampleRank, a learning method based ranking.}, } @inproceedings{DBLP:conf/CEAS_submission/Culotta07, author = {Chris Pal and Xuerui Wang and Andrew McCallum}, title = {Transfer Learning for Enhancing Information Flow in Organizations and Social Networks}, booktitle = {Submitted to Conference on Email and Spam (CEAS), 2007. Technical Note}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/darts-ceas07s.pdf}, sum = {Continuous hidden varable conditional random field for CC prediction/suggestion in email.}, } @inproceedings{DBLP:conf/NESCAI/Culotta07, author = {Aron Culotta and Andrew McCallum and Bart Selman and Ashish Sabharwal}, title = {Sparse Message Passing Algorithms for Weighted Maximum Satisfiability}, booktitle = {New England Student Symposium on Artificial Intelligence (NESCAI)}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/culotta07sparse.pdf}, sum = {A new algorithm for solving weighted maximum satisfiability (WMAX-SAT) problems that divides a large problem into sub-problems, and coordinates the global solution by message passing with sparse messages. Inspired by the desire to do joint-inference in (a) large weighted logics ala Markov Logic Networks, (b) large NLP pipelines, in which there are efficient pre-existing (dynamic programming) solutions to sub-parts of the pipeline. Positive results versus WalkSAT!}, } @inproceedings{DBLP:conf/BiocreativeII/Ganchev07, author = {Kuzman Ganchev and Koby Crammer and Fernando Pereira and Gideon Mann and Kedar Bellare and Andrew McCallum and Steven Carroll and Yang Jin and and Peter White}, title = {Penn/UMass/CHOP BiocreativeII Systems}, booktitle = {BiocreativeII Evaluation Workshop}, year = {2007}, url = {https://people.cs.umass.edu/~mccallum/papers/biocreativeII07.pdf}, sum = {Description of our high-ranking entry in the competition for extraction and linkage from bioinformatics text.}, } @inproceedings{DBLP:conf/nips_ws/Pal06, author = {Chris Pal and Michael Kelm and Xuerui Wang and Greg Druck and Andrew McCallum}, title = {On Discriminative and Semi-Supervised Dimensionality Reduction}, booktitle = {Advances in Neural Information Processing Systems, Workshop on Novel Applications of Dimensionality Reduction (NIPS Workshop)}, year = {2006}, url = {https://people.cs.umass.edu/~mccallum/papers/umass-nips-06-odssdr.pdf}, sum = {Using Multi-Conditional Learning, learn to distribute mixture components just were needed to address some discriminative task. See compelling figure on synthetic overlapping spiral data.}, } @inproceedings{DBLP:conf/icml_ws/Culotta06, author = {Aron Culotta and Andrew McCallum}, title = {Tractable Learning and Inference with Higher-Order Representations}, booktitle = {ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS)}, year = {2006}, url = {https://people.cs.umass.edu/~mccallum/papers/tractable-icmlws06.pdf}, sum = {When working with CRFs having features based on first-order logic, the "unrolled" graphical model would be far to large to fully instantiate. This paper describes a method leveraging MCMC to perform inference and learning while only partially instantiating the model. Positive results on entity resolution (of research papr authors) are described.}, } @inproceedings{DBLP:conf/icml_ws/Pal06, author = {Chris Pal and Andrew McCallum}, title = {CC Prediction with Graphical Models}, booktitle = {Conference on Email and Anti-Spam (CEAS)}, year = {2006}, url = {https://people.cs.umass.edu/~mccallum/papers/ccpred-ceas06.pdf}, sum = {Help keep an organization coordinated by suggesting who to carbon-copy on your outgoing email message.}, } @inproceedings{DBLP:conf/hlt_ws/Culotta06, author = {Aron Culotta and Andrew McCallum}, title = {Practical Markov Logic Containing First-order Quantifiers with Application to Identity Uncertainty}, booktitle = {HLT Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing}, year = {2006}, url = {https://people.cs.umass.edu/~mccallum/papers/practical-hltws06.pdf}, sum = {Markov Logic Networks are Conditional Random Fields that use first-order logic to define features and parameter tying patterns. Making such models scale to non-trivial data set sizes is a challenge because the size of the full instantiation of the model is exponential in the arity of the formulae. Here we describe a method of partial instantiation that allows such models to scale to entity resolution problems millions of entity mentions. On both citation and author entity resolution problems we show that inclusing such first-order features provides increases in accuracy.}, } @inproceedings{DBLP:conf/aaai_ws/Wang06, author = {Xuerui Wang and Wei Li and and Andrew McCallum}, title = {A Continuous-Time Model of Topic Co-occurrence Trends}, booktitle = {AAAI Workshop on Event Detection (AAAI WS)}, year = {2006}, url = {https://people.cs.umass.edu/~mccallum/papers/pamtot-aaaiws06.pdf}, sum = {Capture the time distributions not only of a topics, but also of their co-occurrences. For example, notice that while NLP and ML have both been around for a long time, but their co-occurrence has been rising recently. The model is effectively a combination of the Pachinko Allocation Model (PAM) and Topics-Over-Time (TOT).}, } @article{DBLP:journals/book/Sutton06, author = {Charles Sutton and Andrew McCallum}, title = {An Introduction to Conditional Random Fields for Relational Learning}, journal = {Book chapter in Introduction to Statistical Relational Learning}, editor = {Lise Getoor and Ben Taskar}, year = {2006}, publisher = {MIT Press}, url = {https://people.cs.umass.edu/~mccallum/papers/crf-tutorial.pdf}, sum = {An overview and introduction to conditional random fields for beginners and experts alike---motivation, background, mathematical foundations, linear-chain form, general-structure form, inference, parameter estimation, tips and tricks, an example application to information extraction with a skip-chain structure.}, } @article{DBLP:journals/book/Sutton06, author = {Kamal Nigam and Andrew McCallum and Tom Mitchell}, title = {Semi-supervised Text Classification Using EM}, journal = {Book chapter in Semi-Supervised Learning}, editor = {Chapelle, O., Zien, A., and Scholkopf, B.}, year = {2006}, publisher = {MIT Press}, url = {https://people.cs.umass.edu/~mccallum/papers/semisup-em.pdf}, sum = {Overview, description, experiments on using expectation maximization with naive Bayes text classifiers for learning from labeled and unlabeled data. A chapter in a book about various methods of semi-supervised learning.}, } @article{DBLP:journals/umass/Wang05, author = {Xuerui Wang and Andrew McCallum}, title = {A Note on Topical N-grams}, journal = {University of Massachusetts Technical Report UM-CS-2005-071 (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/tng-tr05.pdf}, sum = {Discover topics like Latent Dirichlet Allocation, but model phrases in addition to single words on a per-topic basis. For example, in the Politics topic, "white house" has special meaning as a colocation, while in the RealEstate topic, modeling the individual words is sufficient. Our TNG model produces much cleaner, more interpretable topics.}, } @inproceedings{DBLP:conf/nips_ws/Li05, author = {Wei Li and Andrew McCallum}, title = {Pachinko allocation: A Directed Acyclic Graph for Topic Correlations}, booktitle = {NIPS Workshop on Nonparametric Bayesian Methods (NIPS WS)}, year = {2005}, sum = {Similar motivations to Blei and Lafferty's Correlated Topic Model (CTM), but uses a DAG to capture arbitrary and possibly sparse correlations among topics. Interior nodes of the DAG have a Dirichlet distribution over their children; words are in the leaves. Provides improved interpretability and classification, as well as improved held-out likelihood over CTM. See ICML 2006 paper above.}, } @article{DBLP:journals/ciir/Metzler05, author = {Don Metzler, W. Bruce Croft and Andrew McCallum}, title = {Direct Maximization of Rank-Based Metrics for Information Retrieval}, journal = {CIIR Technical Report IR-429 (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/direct-metzler05.pdf}, } @inproceedings{DBLP:conf/nips_ws/Li05, author = {Aron Culotta and Andrew McCallum}, title = {Learning Clusterwise Similarity with First-order Features}, booktitle = {NIPS Workshop on the Theoretical Foundations of Clustering (NIPS WS)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/culotta05learning.pdf}, sum = {Discriminatively-trained graph-partitioning methods for clustering, with features over entire clusters, including existential and universal quanifiers. Efficiently instantiate these features only on demand.}, } @article{DBLP:journals/ciir/SuttonMM05, author = {Charles Sutton and Michael Sindelar and Andrew McCallum}, title = {Feature Bagging: Preventing Weight Undertraining in Structured Discriminative Learning}, journal = {Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-402 (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/ir402bags.pdf}, sum = {Avoid a common under-appreciated problem: overly heavy reliance on a few discriminative features which may not be as reliably present in the testing data. Discusses four methods of separate training and combination, and presents statistically-significant improvements---including new best results on CoNLL-2000 NP Chunking.} } @article{DBLP:journals/ciir/SuttonM05, author = {Charles Sutton and Andrew McCallum}, title = {Fast, Piecewise Training for Discriminative Finite-state and Parsing Models}, journal = {Center for Intelligent Information Retrieval Technical Report IR-403 (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/nota-ir403.pdf}, sum = {Further results with "piecewise training", a method also described in a UAI'05 paper.} } @article{DBLP:journals/ciir/Culotta05, author = {Aron Culotta and Andrew McCallum}, title = {Practical Markov Logic Containing First-order Quantifiers with Application to Identity Uncertainty}, journal = {Technical Report IR-430, University of Massachusetts (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/culotta05practical.pdfs}, sum = {Use existental and universal quantifiers in Markov Logic, doing so practially and efficiently by incrementally instantiating these terms as needed. Applied to object correspondence, this model combines the expressivity of BLOG with the predictive accuracy advantages of conditional probability training. Experiments on citation matching and author disambiguation.} } @article{DBLP:journals/ciir/Culotta05b, author = {Aron Culotta and Andrew McCallum}, title = {A Conditional Model of Deduplication for Multi-type Relational Data}, journal = {Technical Report IR-443, University of Massachusetts (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/culotta05conditional.pdf}, sum = {Leverage relations among multiple entity types to perform coreference collectively among all types. Uses CRF-style graph partitioning with a learned distance metric. Experimental results on joint coreference of both citations and their venues showing that accuracy on both improves.} } @article{DBLP:journals/umass/McCallum05, author = {Andrew McCallum and Xuerui Wang and Chris Pal}, title = {Predictive Random Fields: Latent Variable Models Fit by Multiway Conditional Probability with Applications to Document Analysis}, journal = {UMass Technical Report UM-CS-2005-053, version 2.1 (TR)}, year = {2005}, url = {http://www.cs.cmu.edu/afs/cs/Web/People/xuerui/papers/prf.pdf}, sum = {Cluster structured, relational data, like Latent Dirichlet Allocation and its successors, but with undirected graphical models that are conditionally-trained. Improved results over Jebara-inspired synthetic data, and over the Harmonium as tested on an information retreival task. This is an evolving Tech Report, which needs to be updated---in particular we are now referring to this method as "Multi-Conditional Learning" or "Multi-Conditional Mixtures".} } @article{DBLP:journals/umass/McCallum05, author = {Aron Culotta and David Kulp and Andrew McCallum}, title = {Gene Prediction with Conditional Random Fields}, journal = {Technical Report UM-CS-2005-028, University of Massachusetts, Amherst (TR)}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/crfgene.pdf}, sum = {Use finite-state CRFs to locate introns and exons in DNA sequences. Shows the advantages of CRFs' ability to straightforwardly incorporate homology evidence from protein databases.} } @inproceedings{DBLP:conf/uai_submission/Li05, author = {Chris Pal and Charles Sutton and Andrew McCallum}, title = {Constrained Kronecker Deltas for Fast Approximate Inference and Estimation}, booktitle = {Submitted to UAI}, year = {2005}, url = {https://people.cs.umass.edu/~mccallum/papers/crfbeam-uai05s.pdf}, sum = {Sometimes the graph of the graphical model is not large and complex, but the cardinality of the variables is large. This paper describes a new and generalized method for beam search on graphical models, showing positive experimental results for both inference and training. Experiments on NetTalk.}, } @article{DBLP:journals/umass/McCallumS04, author = {Andrew McCallum and Charles Sutton}, title = {Piecewise Training with Parameter Independence Diagrams: Comparing Globally- and Locally-trained Linear-chain CRFs}, journal = {Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-383 (TR)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/lcrf-nips2004.pdf}, sum = {Also presented at NIPS 2004 Workshop on Learning with Structured Outputs. Large undirected graphical models are expensive to train because they require global inference to calculate the gradient of the parameters. We describe a new method for fast training in locally-normalized pieces. Amazingly the resulting models also give higher accuracy than their globally-trained counterparts.}, } @article{DBLP:journals/umass/Bekkerman04, author = {Ron Bekkerman and Andrew McCallum and Gary Huang}, title = {Automatic Categorization of Email into Folders: Benchmark Experiments on Enron and SRI Corpora}, journal = {Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-383 (TR)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/foldering-tr05.pdf}, sum = {Extensive experiments on real-world email foldering.}, } @article{DBLP:journals/umass/McCallumCW04, author = {Andrew McCallum and Andres Corrada-Emmanuel and Xuerui Wang}, title = {The Author-Recipient-Topic Model for Topic and Role Discovery in Social Networks: Experiments with Enron and Academic Email}, journal = {Technical Report UM-CS-2004-096 (TR)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/art04tr.pdf}, sum = {Also presented the NIPS'04 Workshop on " Structured Data and Representations in Probabilistic Models for Categorization") (Social network analysis that not only models links between people, but the word content of the messages exchanged between them. Discovers salient topics guided by the sender-recipient structure in data, and provides improved ability to measure role-similarity between people. A generative model in the style of Latent Dirichlet Allocation.}, } @inproceedings{DBLP:conf/icml_ws/Sutton04, author = {Charles Sutton and Andrew McCallum}, title = {Collective Segmentation and Labeling of Distant Entities in Information Extraction}, booktitle = {ICML workshop on Statistical Relational Learning (ICML WS)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/collseg04icmlws.pdf}, sum = {Makes the boundaries and types of distant segments inter-dependent by augmenting a linear-chain CRF with additional long, arching edges. Approximate inference by Tree-Reparameterization.}, } @inproceedings{DBLP:conf/icml_ws/Raghavan04, author = {Hema Raghavan and James Allan and Andrew McCallum}, title = {An Exploration of Entity Models, Collective Classification and Relation Description}, booktitle = {KDD Workshop on Link Analysis and Group Detection (KDD WS)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/raghavan94kdd.pdf}, sum = {Part of a student synthesis project: includes an application of RMNs to classifying people in newswire.}, } @inproceedings{DBLP:conf/mlsp_ws/Weinman04, author = {Jerod Weinman and Al Hansen and Andrew McCallum}, title = {Sign Detection in Natural Images with Conditional Random Fields}, booktitle = {IEEE International Workshop on Machine Learning for Signal Processing}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/weinman04sign.pdf}, sum = {Part of a student synthesis project: a grid-shaped CRF with inference by belief-propagation with Tree-Reparameterization.}, } @inproceedings{DBLP:conf/naacl/Culotta04, author = {Aron Culotta and Andrew McCallum}, title = {Confidence Estimation for Information Extraction}, booktitle = {Proceedings of Human Language Technology Conference and North American Chapter of the Association for Computational Linguistics (HLT-NAACL)}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/crfcp-hlt04.pdf}, sum = {How to provide not only an answer, but a formally-justified confidence in that answer--using contrained forward-backward.}, desc = {Short Paper} } @article{DBLP:journals/umass/Li04, author = {Wei Li and Andrew McCallum}, title = {A Note on Semi-supervised Learning using Markov Random Fields}, journal = {Technical Note, February 3, 2004}, year = {2004}, url = {https://people.cs.umass.edu/~mccallum/papers/li-ssmrf.pdf}, sum = {A general framework for semi-supervised learning in Conditional Random Fields, with a focus on learning the distance metric between instances. Experimental results with collective classification of documents.}, } @inproceedings{DBLP:conf/nips_ws/McCallum03, author = {Andrew McCallum and Khashayar Rohanimanesh and Charles Sutton}, title = {Dynamic Conditional Random Fields for Jointly Labeling Multiple Sequences}, booktitle = {NIPS*2003 Workshop on Syntax, Semantics, Statistics (NIPS WS)}, year = {2003}, url = {https://people.cs.umass.edu/~mccallum/papers/dcrf-nips03.pdf}, sum = {Workshop version of ICML 2004 paper.}, } @inproceedings{DBLP:conf/ijcai_ws/McCallum03, author = {Andrew McCallum and David Jensen}, title = {A Note on the Unification of Information Extraction and Data Mining using Conditional-Probability, Relational Models}, booktitle = {IJCAI'03 Workshop on Learning Statistical Models from Relational Data (IJCAI WS)}, year = {2003}, url = {https://people.cs.umass.edu/~mccallum/papers/iedatamining-ijcaiws03.pdf}, sum = {Describes big-picture motivation and approach for research that performs information extraction and data mining in an integrated fashion, rather than in two separate serial steps. Lays out a major thrust of my current research over a multi-year span.}, } @inproceedings{DBLP:conf/kdd_ws/McCallum03, author = {Andrew McCallum and Ben Wellner}, title = {Object Consolidation by Graph Partitioning with a Conditionally-trained Distance Metric}, booktitle = {KDD Workshop on Data Cleaning, Record Linkage and Object Consolidation (KDD WS)}, year = {2003}, url = {https://people.cs.umass.edu/~mccallum/papers/condid-kddws2003.pdf}, sum = {Later, improved version of workshop paper: Toward Conditional Models of Identity Uncertainty with Application to Proper Noun Coreference. Andrew McCallum and Ben Wellner. IJCAI Workshop on Information Integration on the Web, 2003.}, } @inproceedings{DBLP:conf/software/McCallum01, author = {Dallan Quass and Andrew McCallum and William Cohen}, title = {Unlocking the Information in Text}, booktitle = {The Future of Software, Winter 2000/2001}, year = {2001}, sum = {An overview of text mining for the Web.}, } @inproceedings{chang1999creating, title={Creating customized authority lists}, author={Huan Chang and David Cohn and Andrew McCallum}, booktitle={Proceedings of the 17th International Conference on Machine Learning (ICML)}, year={1999}, url={https://pdfs.semanticscholar.org/5aa8/92f8d688ada136964d0685f593aabfa8e962.pdf} } @inproceedings{DBLP:conf/aaai_submission/McCallum00, author = {David Cohn and Rich Caruana and Andrew McCallum}, title = {Semi-supervised Clustering with User Feedback}, booktitle = {Submitted to AAAI 2000}, url = {http://www.eecs.tufts.edu/~ebrown/class/rml/SemisupervisedClusteringWithUserFeedback.pdf}, year = {2000}, } @inproceedings{DBLP:conf/aaai_ws/McCallum99, author = {Andrew McCallum}, title = {Multi-Label Text Classification with a Mixture Model Trained by EM}, booktitle = {AAAI'99 Workshop on Text Learning (AAAI WS)}, year = {1999}, url = {http://www.eecs.yorku.ca/course_archive/2005-06/F/6002B/Readings/multilabel.pdf}, sum = {Revised version of paper appearing in AAAI'99 Workshop on Text Learning} } @inproceedings{DBLP:conf/nips_submission/Baker99, author = {Doug Baker and Thomas Hofmann and Andrew McCallum and Yiming Yang}, title = {A Hierarchical Probabilistic Model for Novelty Detection in Text}, booktitle = {Submitted to NIPS'99}, url = {https://people.cs.umass.edu/~mccallum/papers/tdt-nips99s.ps}, year = {1999}, } @inproceedings{DBLP:conf/ijcai_ws/Nigam99, author = {Kamal Nigam and John Lafferty and Andrew McCallum}, title = {Using Maximum Entropy for Text Classification}, booktitle = {IJCAI'99 Workshop on Information Filtering (IJCAI WS)}, url = {http://www.kamalnigam.com/papers/maxent-ijcaiws99.pdf}, year = {1999}, } @inproceedings{DBLP:conf/aaai_ws/Frietag99, author = {Dayne Frietag and Andrew McCallum}, title = {Information Extraction with HMMs and Shrinkage}, booktitle = {AAAI'99 Workshop on Machine Learning for Information Extraction (AAAI WS)}, url = {https://people.cs.umass.edu/~mccallum/papers/ieshrink-aaaiws99.pdf}, year = {1999}, } @inproceedings{DBLP:conf/aaai_ws/Seymore99, author = {Kristie Seymore and Andrew McCallum and Roni Rosenfeld}, title = {Learning Hidden Markov Model Structure for Information Extraction}, booktitle = {AAAI'99 Workshop on Machine Learning for Information Extraction (AAAI WS)}, url = {https://www.cs.cmu.edu/~roni/papers/iestruct-aaaiws99.pdf}, year = {1999}, } @inproceedings{DBLP:conf/aaai_ws/Jones99, author = {Rosie Jones and Andrew McCallum and Kamal Nigam and Ellen Riloff}, title = {Bootstrapping for Text Learning Tasks}, booktitle = {IJCAI-99 Workshop on Text Mining: Foundations, Techniques and Applications (IJCAI WS)}, url = {http://www.kamalnigam.com/papers/bootstrap-ijcaiws99.pdf}, year = {1999}, } @inproceedings{DBLP:conf/aaai_ws/McCallum99, author = {Andrew McCallum and Kamal Nigam and Jason Rennie and Kristie Seymore}, title = {Building Domain-Specific Search Engines with Machine Learning Techniques}, booktitle = {AAAI-99 Spring Symposium (AAAI-SS)}, url = {https://www.ri.cmu.edu/pub_files/pub1/mccallum_andrew_1999_2/mccallum_andrew_1999_2.pdf}, year = {1999}, } @inproceedings{DBLP:conf/aaai_ws/McCallum98, author = {Andrew McCallum and Kamal Nigam}, title = {A Comparison of Event Models for Naive Bayes Text Classification}, booktitle = {AAAI-98 Workshop on "Learning for Text Categorization" (AAAI WS)}, url = {http://staff.icar.cnr.it/manco/Teaching/2005/datamining/articoli/multinomial-aaaiws98.pdf}, year = {1998}, } @inproceedings{DBLP:conf/aaai_ws/McCallum97, author = {Andrew McCallum}, title = {Efficient Exploration in Reinforcement Learning with Hidden State}, booktitle = {AAAI Fall Symposium on "Model-directed Autonomous Systems"}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.17.227&rep=rep1&type=pdf}, year = {1997}, } @article{DBLP:journals/tsmc/McCallum96, author = {Andrew McCallum}, title = {Hidden State and Reinforcement Learning with Instance-Based State Identification}, journal = {IEEE Transations on Systems, Man and Cybernetics, Special issue on Robot Learning}, year = {1996}, url = {https://pdfs.semanticscholar.org/1fb6/57ed848dfee9b8fd2f3a167f5842c9a474c8.pdf}, volume = { 26 }, number = { 3 }, pages = { 464--473 }, } @inproceedings{DBLP:conf/aaai_ws/McCallum97, author = {Andrew McCallum}, title = {Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks}, booktitle = {From Animals to Animats, Fourth International Conference on Simulation of Adaptive Behavior, (SAB'96). Cape Cod, Massachusetts.}, url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=A39E3702653F77F02B1DFDF4FD3EFDF9?doi=10.1.1.46.3832&rep=rep1&type=pdf}, year = {1996}, } @article{DBLP:journals/phd_thesis/McCallum95, author = {Andrew McCallum}, title = {Reinforcement Learning with Selective Perception and Hidden State}, journal = {PhD. thesis}, year = {1995}, url = {http://web.media.mit.edu/~tristan/Classes/MAS.945/Papers/Contextual/McCallum_Thesis.pdf}, } @article{DBLP:journals/urcs/McCallum94, author = {Andrew McCallum}, title = {First Results with Instance-Based State Identification for Reinforcement Learning}, journal = {URCS Tech Report 502 (TR)}, year = {1994}, url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=87927F799EAD4EA424D7F1B5B82213F1?doi=10.1.1.51.6428&rep=rep1&type=pdf}, } @inproceedings{DBLP:conf/iml_ws/McCallum94, author = {Andrew McCallum}, title = {Reduced Training Time for Reinforcement Learning with Hidden State}, booktitle = {The Proceedings of the Eleventh International Machine Learning Workshop, Robot Learning, New Brunswick, NJ}, url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=2F33028FD5E7155F64A72ABD19B4F1E3?doi=10.1.1.51.5045&rep=rep1&type=pdf}, year = {1994}, } @inproceedings{DBLP:conf/iml_ws/McCallum94, author = {Andrew McCallum}, title = {Short-Term Memory in Visual Routines for `Off-Road Car Chasing'}, booktitle = {Working Notes of AAAI Spring Symposium Series, "Toward Physical Interaction and Manipulation", Stanford University, March 21-23}, url = {http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=594CD7E4AFC804DFF1D5912C90556EAD?doi=10.1.1.50.6117&rep=rep1&type=pdf}, year = {1994}, } @article{DBLP:journals/thesis_proposal/McCallum93, author = {Andrew McCallum}, title = {Learning with Incomplete Selective Perception}, journal = {URCS Tech Report 453 (TR)}, year = {1993}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.53.7986&rep=rep1&type=pdf}, } @inproceedings{DBLP:conf/usenix/Garret93, author = {William E Garrett and Michael L Scott and Ricardo Bianchini and Leonidas I Kontothanassis and Andrew McCallum and Jeffrey A Thomas and Robert W Wisniewski and Steve Luk}, title = {Linking Shared Segments}, booktitle = {Winter USENIX, San Diego, CA}, year = {1993}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.18.760&rep=rep1&type=pdf}, } @article{DBLP:journals/urcs/McCallum92, author = {Andrew McCallum}, title = {First Results with Utile Distinction Memory for Reinforcement Learning}, journal = {URCS Tech Report 446 (TR)}, year = {1992}, url = {https://dl.acm.org/citation.cfm?id=898336}, } @article{DBLP:journals/urcs/Garrett92, author = {William E Garrett and LI Bianchini and LI Kontothanassis and Andrew McCallum and Jeffery Thomas and Robert Wisniewski and Michael L Scott}, title = {Dynamic Sharing and Backward Compatibility on 64-Bit Machines}, journal = {URCS Tech Report 418 (TR)}, year = {1992}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.50.6867&rep=rep1&type=pdf}, } @inproceedings{DBLP:conf/naacl/Verga18, author = {Patrick Verga and Emma Strubell and Andrew McCallum}, title = {Simultaneously Self-attending to All Mentions for Full-Abstract Biological Relation Extraction }, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL)}, year = {2018}, url = {https://arxiv.org/abs/1802.10569}, code = {https://github.com/patverga/bran} } @inproceedings{DBLP:conf/naacl/Rooshenas18, author = {Amirmohammad Rooshenas and Aishwarya Kamath and Andrew McCallum}, title = {Training Structured Prediction Energy Networks with Indirect Supervision}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL)}, year = {2018}, desc = {Oral presentation} } @inproceedings{conf/TextGraph18/Chang18, author = {Haw-Shiuan Chang and Amol Agrawal and Ananya Ganesh and Anirudha Desai and Vinayak Mathur and Alfred Hough and Andrew McCallum}, title = {Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings}, booktitle = {TextGraphs-12: the Workshop on Graph-based Methods for Natural Language Processing (NAACL WS)}, year = {2018}, slides = {http://docs.wixstatic.com/ugd/e150d8_ae5222766cda446985cce83c1c72bae3.pdf}, url = {https://arxiv.org/abs/1804.03257}, } @inproceedings{DBLP:conf/acl/Murty18, author = {Shikhar Murty* and Patrick Verga* and Luke Vilnis and Irena Radovanovic and Andrew McCallum (* indicates Equal Contribution)}, title = {Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2018}, desc = {Oral presentation}, url = {http://aclweb.org/anthology/P18-1010} } @inproceedings{DBLP:conf/acl/Vilnis18, author = {Luke Vilnis* and Xiang Li* and Shikhar Murty and Andrew McCallum (* indicates Equal Contribution)}, title = {Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures}, booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2018}, url = {http://people.cs.umass.edu/~luke/box-lattices.pdf} } @inproceedings{conf/nips_ws/TraylorMDM17, title = {Learning String Alignments for Entity Aliases}, author = {Aaron Traylor and Nicholas Monath and Rajarshi Das and Andrew McCallum}, year = {2017}, booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS}, url = {http://www.akbc.ws/2017/papers/28_paper.pdf}, code = {https://github.com/iesl/learned-string-alignments} } @inproceedings{conf/nips_ws/KobrenMM17, title = {Entity-centric Attribute Feedback for Interactive Knowledge Bases}, author = {Ari Kobren and Nicholas Monath and Andrew McCallum}, year = {2017}, booktitle = {6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS}, url = {http://www.akbc.ws/2017/papers/27_paper.pdf} } @inproceedings{conf/nips_ws/MonathKKM17, title={Gradient-based Hierarchical Clustering}, author={Nicholas Monath and Ari Kobren and Akshay Krishnamurthy and Andrew McCallum}, year = {2017}, booktitle = {NIPS Workshop on Discrete Structures in Machine Learning (DISCML)}, desc = {Oral Presentation} } @inproceedings{DBLP:conf/nips/GreenbergMKFMM18, author = {Craig Greenberg and Nicholas Monath and Ari Kobren and Patrick Flaherty and Andrew McGregor and Andrew McCallum}, title = {Compact Representation of Uncertainty in Clustering}, year = {2018}, booktitle = {Advances in Neural Information Processing Systems (NIPS)} } @inproceedings{thai2018embedded, title={Embedded-State Latent Conditional Random Fields for Sequence Labeling}, author={Thai, Dung and Ramesh, Sree Harsha and Murty, Shikhar and Vilnis, Luke and McCallum, Andrew}, booktitle={Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL)}, year={2018}, url = {https://arxiv.org/abs/1809.10835} } @inproceedings{strubell2018linguistically, title={Linguistically-Informed Self-Attention for Semantic Role Labeling}, author={Strubell, Emma and Verga, Patrick and Andor, Daniel and Weiss, David and McCallum, Andrew}, booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year={2018}, url = {https://arxiv.org/abs/1804.08199}, desc = {Best paper award} } @inproceedings{greenberg2018marginal, title={Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets}, author={Greenberg, Nathan and Bansal, Trapit and Verga, Patrick and McCallum, Andrew}, booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year={2018}, url = {http://aclweb.org/anthology/D18-1306}, desc = {Oral Presentation} } @inproceedings{das2018go, title={Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning}, author={Rajarshi Das and Shehzaad Dhuliawala and Manzil Zaheer and Luke Vilnis and Ishan Durugkar and Akshay Krishnamurthy and Alex Smola and Andrew McCallum}, booktitle={International Conference on Learning Representations (ICLR)}, year={2018}, url = {https://arxiv.org/abs/1711.05851}, code = {https://github.com/shehzaadzd/MINERVA} } @inproceedings{das2019multi-step, title={Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering}, author={Rajarshi Das and Shehzaad Dhuliawala and Manzil Zaheer and Andrew McCallum}, booktitle={International Conference on Learning Representations (ICLR)}, year={2019}, url = {https://openreview.net/forum?id=HkfPSh05K7} } @inproceedings{das2019building, title={Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension}, author={Rajarshi Das and Shehzaad Dhuliawala and Manzil Zaheer and Andrew McCallum}, booktitle={International Conference on Learning Representations (ICLR)}, year={2019}, url = {https://openreview.net/forum?id=S1lhbnRqF7} } @inproceedings{li2019smoothing, title={Smoothing the Geometry of Box Embeddings}, author={Xiang Li and Luke Vilnis and Dongxu Zhang and Michael Boratko and Andrew McCallum}, booktitle={International Conference on Learning Representations (ICLR)}, year={2019}, url = {https://openreview.net/forum?id=H1xSNiRcF7}, desc = {Oral Presentation} } @inproceedings{zhang2019openki, title={OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference}, author={Zhang, Dongxu and Mukherjee, Subhabrata and Lockard, Colin and Dong, Luna and McCallum, Andrew}, booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, pages={762--772}, year={2019}, url = {https://www.aclweb.org/anthology/N19-1083} } @inproceedings{yadav2019supervised, title={Supervised Hierarchical Clustering with Exponential Linkage}, author={Nishant Yadav and Ari Kobren and Nicholas Monath and Andrew McCallum}, booktitle={International Conference on Machine Learning (ICML)}, year={2019}, url = {http://proceedings.mlr.press/v97/yadav19a/yadav19a.pdf}, code = {https://github.com/iesl/expLinkage} } @inproceedings{kobren2019feedback, title={Integrating User Feedback under Identity Uncertainty in Knowledge Base Construction}, author={Kobren, Ari and Monath, Nicholas and McCallum, Andrew}, booktitle={Automated Knowledge Base Construction (AKBC)}, year={2019}, url={https://openreview.net/forum?id=SygLHbcapm} } @inproceedings{tam2019optimal, title={Optimal Transport-based Alignment of Learned Character Representations for String Similarity}, author={Tam, Derek and Monath, Nicholas and Kobren, Ari and Traylor, Aaron and Das, Rajarshi and McCallum, Andrew}, booktitle={Association of Computational Linguistics (ACL)}, year={2019}, desc={Oral} } @inproceedings{monath2019grinch, title={Scalable Hierarchical Clustering with Tree Grafting}, author={Monath*, Nicholas and Kobren*, Ari and Krishnamurthy, Akshay and Glass, Michael and McCallum, Andrew}, booktitle={International Conference on Knowledge Discovery and Data Mining (KDD)}, year={2019}, desc={Oral} } @inproceedings{kobren2019matching, title={Paper Matching with Local Fairness Constraints}, author={Kobren, Ari and Saha, Barna and McCallum, Andrew}, booktitle={International Conference on Knowledge Discovery and Data Mining (KDD)}, year={2019}, code={https://github.com/iesl/fair-matching}, url={https://arxiv.org/abs/1905.11924}, desc={Oral} } @inproceedings{monath2019gradient, title={Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space}, author={Nicholas Monath and Manzil Zaheer and Daniel Silva and Andrew McCallum and Amr Ahmed}, booktitle={International Conference on Knowledge Discovery and Data Mining (KDD)}, year={2019} } @inproceedings{mysore2017automatically, title={Automatically Extracting Action Graphs from Materials Science Synthesis Procedures}, author={Sheshera Mysore and Edward Kim and Emma Strubell and Ao Liu and Haw-Shiuan Chang and Srikrishna Kompella and Kevin Huang and Andrew McCallum and Elsa Olivetti}, booktitle={Workshop on Machine Learning for Molecules and Materials at NIPS}, year={2017}, url={https://arxiv.org/abs/1711.06872} } @inproceedings{mysore2019msannlaw, title={The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures}, author={Sheshera Mysore and Zach Jensen and Edward Kim and Kevin Huang and Haw-Shiuan Chang and Emma Strubell and Jeffrey Flanigan and Andrew McCallum and Elsa Olivetti}, booktitle={Proceedings of the 13th Linguistic Annotation Workshop at ACL}, year={2019}, url={https://sigann.github.io/LAW-XIII-2019/pdf/W19-4007.pdf} } @inproceedings{bansal-etal-2019-a2n, title = "{A}2{N}: Attending to Neighbors for Knowledge Graph Inference", author = "Trapit Bansal and Da-Cheng Juan and Sujith Ravi and Andrew McCallum", booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics", month = jul, year = "2019", address = "Florence, Italy", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/P19-1431", doi = "10.18653/v1/P19-1431", pages = "4387--4392" } @article{chang2019ovecoming, author = {Haw-Shiuan Chang and Shankar Vembu and Sunil Mohan and Rheeya Uppaal and Andrew McCallum}, journal = {Machine Learning}, url = {http://arxiv.org/abs/1911.07335}, title = {Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition}, year={2020}, doi={10.1007/s10994-020-05897-1}, publisher={Springer}, video={https://slideslive.com/38933012/using-error-decay-prediction-to-overcome-practical-issues-of-deep-active-learning-for-named-entity-recognition}, slides={https://docs.google.com/presentation/d/1h3bI1dS8-vS5ItcfGOHN3J7Wi7dnWWBf0gA4-yBXrk4/edit?usp=sharing} } @inproceedings{drozdov2019diora, title={Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders}, author={Drozdov, Andrew and Verga, Patrick and Yadav, Mohit and Iyyer, Mohit and McCallum, Andrew}, booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, year={2019}, url={https://www.aclweb.org/anthology/N19-1116/}, desc={Oral Presentation} } @inproceedings{drozdov2019dioralabeled, title={Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders}, author={Drozdov, Andrew and Verga, Patrick and Chen, Yi-Pei and Iyyer, Mohit and McCallum, Andrew}, booktitle={Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year={2019}, url={https://www.aclweb.org/anthology/D19-1161/} } @inproceedings{drozdov2020sdiora, title="Unsupervised Parsing with {S-DIORA}: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders", author={Drozdov, Andrew and Rongali, Subendhu and Chen, Yi-Pei and O'Gorman, Tim and Iyyer, Mohit and McCallum, Andrew}, booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year={2020} } @inproceedings{diora2021distantdiora, title={Improved Latent Tree Induction with Distant Supervision via Span Constraints}, author={Xu, Zhiyang and Drozdov, Andrew and Lee, Jay Yoon and O{'}Gorman, Tim and Rongali, Subendhu and Finkbeiner, Dylan and Suresh, Shilpa and Iyyer, Mohit and McCallum, Andrew}, booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year={2021} } @inproceedings{drozdov2022amralign, title="Inducing and Using Alignments for Transition-based {AMR} Parsing", author={Drozdov, Andrew and Zhou, Jiawei and Florian, Radu and McCallum, Andrew and Naseem, Tahira and Kim, Yoon and Astudillo, Ramon Fernandez}, booktitle={Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, year={2022} } @inproceedings{drozdov2022knnlm, title = "You can't pick your neighbors, or can you? {W}hen and how to rely on retrieval in the {kNN-LM}", author = "Andrew Drozdov and Shufan Wang and Razieh Rahimi and Andrew McCallum and Hamed Zamani and Mohit Iyyer", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022", year = "2022" } @inproceedings{DBLP:conf/clef/KommarajuGLBMWI20, author={Vaishnavi Kommaraju and Karthick Gunasekaran and Kun Li and Trapit Bansal and Andrew McCallum and Ivana Williams and Ana-Maria Istrate}, title={Unsupervised Pre-training for Biomedical Question Answering}, year={2020}, cdate={1577836800000}, url={http://ceur-ws.org/Vol-2696/paper_144.pdf}, booktitle={CLEF (Working Notes)}, crossref={conf/clef/2020w} } @inproceedings{bansal2020simultaneously, title={Simultaneously linking entities and extracting relations from biomedical text without mention-level supervision}, author={Bansal, Trapit and Verga, Pat and Choudhary, Neha and McCallum, Andrew}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={34}, number={05}, pages={7407--7414}, year={2020} } @inproceedings{bansal2020learning, title={Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks}, author={Bansal, Trapit and Jha, Rishikesh and McCallum, Andrew}, booktitle={Proceedings of the 28th International Conference on Computational Linguistics}, pages={5108--5123}, year={2020} } @inproceedings{bansal2020self, title={Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks}, author={Bansal, Trapit and Jha, Rishikesh and Munkhdalai, Tsendsuren and McCallum, Andrew}, booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={522--534}, year={2020} } @inproceedings{chang2021extending, title={Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications}, author={Haw-Shiuan Chang and Amol Agrawal and Andrew McCallum}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, year={2021}, url={https://arxiv.org/abs/2103.15330}, poster={https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_3d91e4f3cd6746aeaf24407fc0b674d1.pdf}, slides={https://docs.google.com/presentation/d/1k-OBWdBYsGmXUuvNc1_J_JrEppB_Aqh82bJPCgjFL-s/edit?usp=sharing}, } @inproceedings{chang2021changing, title={Changing the Mind of Transformers for Topically-Controllable Language Generation}, author={Haw-Shiuan Chang and Jiaming Yuan and Mohit Iyyer and Andrew McCallum}, booktitle={Conference of the European Chapter of the Association for Computational Linguistics (EACL)}, year={2021}, url={https://arxiv.org/abs/2103.15335}, code={https://github.com/iesl/interactive_LM}, video={https://slideslive.com/38954487/changing-the-mind-of-transformers-for-topicallycontrollable-language-generation}, poster={https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_87e429adfcb9478e86a55033df144458.pdf}, slides={https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_8212c213a26a4c36acc69989aec2399c.key?dn=EACL_interactive_LM.key}, desc={Oral Presentation} } @inproceedings{chang2021multi-facet, title={Multi-facet Universal Schema}, author={Rohan Paul* and Haw-Shiuan Chang* and Andrew McCallum}, booktitle={Conference of the European Chapter of the Association for Computational Linguistics (EACL)}, year={2021}, url={https://arxiv.org/abs/2103.15339}, code={https://github.com/rohanpaul11/multifacet-re}, video={https://slideslive.com/38954382/multifacet-universal-schema}, poster={https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_97d81dbfca604d07b825f2214805166a.pdf}, slides={https://f6d60bef-de96-4b94-b613-4913f88f2f0f.filesusr.com/ugd/e150d8_b646fb0d748f43f788131a2dee5e2572.key?dn=EACL_multi-facet_RE_small.key}, desc={Oral Presentation} } @inproceedings{swarup-etal-2020-instance, title = "{A}n {I}nstance {L}evel {A}pproach for {S}hallow {S}emantic {P}arsing in {S}cientific {P}rocedural {T}ext", author = "Daivik Swarup and Ahsaas Bajaj and Sheshera Mysore and Tim O{'}Gorman and Rajarshi Das and Andrew McCallum", booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020", month = Nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.findings-emnlp.270" } @inproceedings{ogorman-etal-2021-ms, title = "{MS}-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural Text", author = "Tim O{'}Gorman and Zach Jensen and Sheshera Mysore and Kevin Huang and Rubayyat Mahbub and Elsa Olivetti and Andrew McCallum", booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing", month = Nov, year = "2021", address = "Online and Punta Cana, Dominican Republic", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2021.emnlp-main.101" } @inproceedings{mysore2021csfcube, title={{CSFC}ube - A Test Collection of Computer Science Research Articles for Faceted Query by Example}, author={Sheshera Mysore and Tim O'Gorman and Andrew McCallum and Hamed Zamani}, booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)}, year={2021}, url={https://openreview.net/forum?id=8Y50dBbmGU}, code={https://github.com/iesl/CSFCube}, } @article{mysore2021aspire, author = {Sheshera Mysore and Arman Cohan and Tom Hope}, title = {Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity}, journal = {CoRR}, year = {2021}, url = {https://arxiv.org/abs/2111.08366}, timestamp = {Mon, 22 Nov 2021 16:44:06 +0100}, code={https://github.com/allenai/aspire} } @inproceedings{angell2020clustering, title={Clustering-based Inference for Biomedical Entity Linking}, author={Rico Angell and Nicholas Monath and Sunil Mohan and Nishant Yadav and Andrew McCallum}, booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, pages = {2598--2608}, year = {2021}, url={https://aclanthology.org/2021.naacl-main.205/} } @inproceedings{yadav2021event, title={Event and Entity Coreference using Trees to Encode Uncertainty in Joint Decisions}, author={Nishant Yadav and Nicholas Monath and Rico Angell and Andrew McCallum}, booktitle={Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference at EMNLP}, pages={100--110}, year={2021}, desc={Best Paper Award}, url={https://aclanthology.org/2021.crac-1.11/} } @inproceedings{yadav2021subsume, title={SUBSUME: A Dataset for Subjective Summary Extraction from Wikipedia Documents}, author={Nishant Yadav* and Matteo Brucato* and Anna Fariha* and Oscar Youngquist and Julian Killingback and Alexandra Meliou and Peter Haas}, booktitle={Proceedings of the Third Workshop on New Frontiers in Summarization at EMNLP}, pages={131--141}, year={2021}, data={https://github.com/afariha/SubSumE}, url={https://aclanthology.org/2021.newsum-1.14/}, } @inproceedings{kennard2022disapere, title={DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions}, author={Kennard, Neha and O’Gorman, Tim and Das, Rajarshi and Sharma, Akshay and Bagchi, Chhandak and Clinton, Matthew and Yelugam, Pranay Kumar and Zamani, Hamed and McCallum, Andrew}, booktitle={Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, pages={1234--1249}, year={2022} } @inproceedings{das2022knowledge, title={Knowledge base question answering by case-based reasoning over subgraphs}, author={Das, Rajarshi and Godbole, Ameya and Naik, Ankita and Tower, Elliot and Zaheer, Manzil and Hajishirzi, Hannaneh and Jia, Robin and McCallum, Andrew}, booktitle={International Conference on Machine Learning (ICML)}, pages={4777--4793}, year={2022}, organization={PMLR} } @inproceedings{das2021case, title={Case-based Reasoning for Natural Language Queries over Knowledge Bases}, author={Das, Rajarshi and Zaheer, Manzil and Thai, Dung and Godbole, Ameya and Perez, Ethan and Lee, Jay Yoon and Tan, Lizhen and Polymenakos, Lazaros and McCallum, Andrew}, booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={9594--9611}, year={2021} } @inproceedings{das2020probabilistic, title={Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion}, author={Das, Rajarshi and Godbole, Ameya and Monath, Nicholas and Zaheer, Manzil and McCallum, Andrew}, booktitle={Findings of the Association for Computational Linguistics: EMNLP 2020 (EMNLP)}, pages={4752--4765}, year={2020} } @inproceedings{das2020simple, title={A Simple Approach to Case-Based Reasoning in Knowledge Bases}, author={Das, Rajarshi and Godbole, Ameya and Dhuliawala, Shehzaad and Zaheer, Manzil and McCallum, Andrew}, booktitle={Automated Knowledge Base Construction (AKBC)}, year={2020} } @inproceedings{boratko2020protoqa, title={ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning}, author={Boratko, Michael and Li, Xiang and O’Gorman, Tim and Das, Rajarshi and Le, Dan and McCallum, Andrew}, booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={1122--1136}, year={2020} } @inproceedings{das2019chains, title={Chains-of-reasoning at textgraphs 2019 shared task: Reasoning over chains of facts for explainable multi-hop inference}, author={Das, Rajarshi and Godbole, Ameya and Zaheer, Manzil and Dhuliawala, Shehzaad and McCallum, Andrew}, booktitle={Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)}, pages={101--117}, year={2019} } @inproceedings{das2019multi, title={Multi-step entity-centric information retrieval for multi-hop question answering}, author={Das, Rajarshi and Godbole, Ameya and Kavarthapu, Dilip and Gong, Zhiyu and Singhal, Abhishek and Yu, Mo and Guo, Xiaoxiao and Gao, Tian and Zamani, Hamed and Zaheer, Manzil and others}, booktitle={Proceedings of the 2nd Workshop on Machine Reading for Question Answering}, pages={113--118}, year={2019} } @inproceedings{boratko2018systematic, title={A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset}, author={Boratko, Michael and Padigela, Harshit and Mikkilineni, Divyendra and Yuvraj, Pritish and Das, Rajarshi and McCallum, Andrew and Chang, Maria and Fokoue-Nkoutche, Achille and Kapanipathi, Pavan and Mattei, Nicholas and others}, booktitle={Proceedings of the Workshop on Machine Reading for Question Answering}, pages={60--70}, year={2018} } @inproceedings{thai2021simultaneously, title={Simultaneously self-attending to text and entities for knowledge-informed text representations}, author={Thai, Dung and Thirukovalluru, Raghuveer and Bansal, Trapit and McCallum, Andrew}, booktitle={Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)}, pages={241--247}, year={2021} } @inproceedings{bansal2021diverse, title={Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP}, author={Bansal, Trapit and Gunasekaran, Karthick Prasad and Wang, Tong and Munkhdalai, Tsendsuren and McCallum, Andrew}, booktitle={Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={5812--5824}, year={2021} } @inproceedings{agarwal2022entity, title={Entity Linking via Explicit Mention-Mention Coreference Modeling}, author={Agarwal, Dhruv and Angell, Rico and Monath, Nicholas and McCallum, Andrew}, booktitle={Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, pages={4644--4658}, year={2022} } @inproceedings{angell2022interactive, title={Interactive Correlation Clustering with Existential Cluster Constraints}, author={Angell, Rico and Monath, Nicholas and Yadav, Nishant and McCallum, Andrew}, booktitle={International Conference on Machine Learning (ICML)}, pages={703--716}, year={2022}, organization={PMLR} } @inproceedings{mishra2022evaluative, title={An Evaluative Measure of Clustering Methods Incorporating Hyperparameter Sensitivity}, author={Mishra, Siddhartha and Monath, Nicholas and Boratko, Michael and Kobren, Ariel and McCallum, Andrew}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, volume={36}, number={7}, pages={7788--7796}, year={2022} } @inproceedings{ray2022sublinear, title={Sublinear Time Approximation of Text Similarity Matrices}, author={Ray, Archan and Monath, Nicholas and McCallum, Andrew and Musco, Cameron}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}, volume={36}, number={7}, pages={8072--8080}, year={2022} } @article{boratko2021capacity, title={Capacity and Bias of Learned Geometric Embeddings for Directed Graphs}, author={Boratko, Michael and Zhang, Dongxu and Monath, Nicholas and Vilnis, Luke and Clarkson, Kenneth L and McCallum, Andrew}, journal={Advances in Neural Information Processing Systems (NeurIPS)}, volume={34}, pages={16423--16436}, year={2021} } @inproceedings{greenberg2021exact, title={Exact and approximate hierarchical clustering using A*}, author={Greenberg, Craig S and Macaluso, Sebastian and Monath, Nicholas and Dubey, Avinava and Flaherty, Patrick and Zaheer, Manzil and Ahmed, Amr and Cranmer, Kyle and McCallum, Andrew}, booktitle={Uncertainty in Artificial Intelligence (UAI)}, pages={2061--2071}, year={2021}, organization={PMLR} } @inproceedings{monath2021scalable, title={Scalable Hierarchical Agglomerative Clustering}, author={Monath, Nicholas and Dubey, Kumar Avinava and Guruganesh, Guru and Zaheer, Manzil and Ahmed, Amr and McCallum, Andrew and Mergen, Gokhan and Najork, Marc and Terzihan, Mert and Tjanaka, Bryon and others}, booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining (KDD)}, pages={1245--1255}, year={2021} } @inproceedings{thirukovalluru2021scaling, title={Scaling within document coreference to long texts}, author={Thirukovalluru, Raghuveer and Monath, Nicholas and Shridhar, Kumar and Zaheer, Manzil and Sachan, Mrinmaya and McCallum, Andrew}, booktitle={Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (ACL)}, pages={3921--3931}, year={2021} } @inproceedings{monath2021dag, title={Dag-structured clustering by nearest neighbors}, author={Monath, Nicholas and Zaheer, Manzil and Dubey, Kumar Avinava and Ahmed, Amr and McCallum, Andrew}, booktitle={International Conference on Artificial Intelligence and Statistics (AISTATS)}, pages={2854--2862}, year={2021}, organization={PMLR} } @inproceedings{chang2022softmax, title={Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions}, author={Chang, Haw-Shiuan and McCallum, Andrew}, booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL)}, pages={8048--8073}, year={2022} } @inproceedings{macaluso2021cluster, title={Cluster trellis: Data structures \& algorithms for exact inference in hierarchical clustering}, author={Macaluso, Sebastian and Greenberg, Craig and Monath, Nicholas and Lee, Ji Ah and Flaherty, Patrick and Cranmer, Kyle and McGregor, Andrew and McCallum, Andrew}, booktitle={International Conference on Artificial Intelligence and Statistics (AISTATS)}, pages={2467--2475}, year={2021}, organization={PMLR} } @inproceedings{thai2020using, title={Using BibTeX to Automatically Generate Labeled Data for Citation Field Extraction}, author={Thai, Dung and Xu, Zhiyang and Monath, Nicholas and Veytsman, Boris and McCallum, Andrew}, booktitle={Automated Knowledge Base Construction (AKBC)}, year={2020} } @inproceedings{tam2020predicting, title={Predicting Institution Hierarchies with Set-based Models}, author={Tam, Derek and Monath, Nicholas and Kobren, Ari and McCallum, Andrew}, booktitle={Automated Knowledge Base Construction (AKBC)}, year={2020} } @inproceedings{dasgupta2021box, title={Box-to-box transformations for modeling joint hierarchies}, author={Dasgupta, Shib Sankar and Li, Xiang Lorraine and Boratko, Michael and Zhang, Dongxu and McCallum, Andrew}, booktitle={Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)}, pages={277--288}, year={2021} } @inproceedings{dasgupta2022word2box, title={Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings}, author={Dasgupta, Shib and Boratko, Michael and Mishra, Siddhartha and Atmakuri, Shriya and Patel, Dhruvesh and Li, Xiang and McCallum, Andrew}, booktitle={Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL)}, pages={2263--2276}, year={2022} } @inproceedings{chen2021probabilistic, title={Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning}, author={Chen, Xuelu and Boratko, Michael and Chen, Muhao and Dasgupta, Shib Sankar and Li, Xiang Lorraine and McCallum, Andrew}, booktitle={Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)}, pages={882--893}, year={2021} } @article{dasgupta2020improving, title={Improving local identifiability in probabilistic box embeddings}, author={Dasgupta, Shib and Boratko, Michael and Zhang, Dongxu and Vilnis, Luke and Li, Xiang and McCallum, Andrew}, journal={Advances in Neural Information Processing Systems (NeurIPS)}, volume={33}, pages={182--192}, year={2020} } @inproceedings{DBLP:conf/akbc/PatelDB0VM20, author = {Dhruvesh Patel and Shib Sankar Dasgupta and Michael Boratko and Xiang Li and Luke Vilnis and Andrew McCallum}, title = {Representing Joint Hierarchies with Box Embeddings}, booktitle = {Conference on Automated Knowledge Base Construction, {AKBC} 2020, Virtual, June 22-24, 2020 (AKBC)}, year = {2020}, crossref = {DBLP:conf/akbc/2020}, url = {https://doi.org/10.24432/C5KS37}, doi = {10.24432/C5KS37}, timestamp = {Tue, 12 Jan 2021 16:51:01 +0100}, biburl = {https://dblp.org/rec/conf/akbc/PatelDB0VM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @inproceedings{patel2021modeling, title={Modeling label space interactions in multi-label classification using box embeddings}, author={Patel, Dhruvesh and Dangati, Pavitra and Lee, Jay-Yoon and Boratko, Michael and McCallum, Andrew}, booktitle={International Conference on Learning Representations (ICLR)}, year={2021} } @inproceedings{boratko2021min, title={Min/max stability and box distributions}, author={Boratko, Michael and Burroni, Javier and Dasgupta, Shib Sankar and McCallum, Andrew}, booktitle={Uncertainty in Artificial Intelligence (UAI)}, pages={2146--2155}, year={2021}, organization={PMLR} } @inproceedings{yadav2022efficient, title={Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization}, author={Nishant Yadav and Nicholas Monath and Rico Angell and Manzil Zaheer and Andrew McCallum}, booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, pages={2171–2194}, year={2022}, url={https://arxiv.org/pdf/2210.12579.pdf}, desc={Oral Presentation}, code={https://github.com/iesl/anncur} } @inproceedings{chang2023multi-cls, title = {Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling}, author = {Chang*, Haw-Shiuan and Sun*, Ruei-Yao and Ricci*, Kathryn and McCallum, Andrew}, booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)}, year = {2023}, url = {https://arxiv.org/abs/2210.05043}, code = {https://github.com/iesl/multicls/} } @inproceedings{chang2023revisiting, title = {Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond}, author = {Chang*, Haw-Shiuan and Yao*, Zonghai and Gon, Alolika and Yu, Hong and McCallum, Andrew}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2023 (Findings of ACL)}, year = {2023}, url = {http://arxiv.org/abs/2305.12289}, code = {https://github.com/iesl/Softmax-CPR} } @inproceedings{chang2024copy, title={To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders}, author={Haw-Shiuan Chang and Nikhil Agarwal and Andrew McCallum}, booktitle={Proceedings of The 17th ACM Inernational Conference on Web Search and Data Mining (WSDM)}, year={2024}, url={https://arxiv.org/pdf/2310.14079}, code={https://github.com/iesl/softmax_CPR_recommend} } @inproceedings{yadav2023efficient, title={Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition}, author={Nishant Yadav and Nicholas Monath and Manzil Zaheer and Andrew McCallum}, booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023}, year={2023}, url={https://arxiv.org/pdf/2305.02996.pdf}, code={https://github.com/iesl/anncur} } @inproceedings{atmakuri2022robustness, TITLE = {{Robustness of Explanation Methods for NLP Models}}, AUTHOR = {Atmakuri, Shriya and Chheda, Tejas and Kandula, Dinesh and Yadav, Nishant and Lee, Taesung and Tuinhof, Hessel}, URL = {https://hal.science/hal-03773445}, BOOKTITLE = {{Workshop on Trustworthy Artificial Intelligence as a part of the ECML/PKDD 22 program}}, ADDRESS = {Grenoble, France, France}, ORGANIZATION = {{IRT SystemX [IRT SystemX]}}, YEAR = {2022}, MONTH = Sep, PDF = {https://hal.science/hal-03773445/file/Camera_Ready.pdf}, HAL_ID = {hal-03773445}, HAL_VERSION = {v1}, } @inproceedings{thai2023machine, title={Machine Reading Comprehension using Case-based Reasoning}, author={Dung Thai and Dhruv Agarwal and Mudit Chaudhary and Wenlong Zhao and Rajarshi Das and Manzil Zaheer and Jay-Yoon Lee and Hannaneh Hajishirzi and Andrew McCallum}, booktitle={Findings of the Association for Computational Linguistics: EMNLP 2023}, year={2023}, url={https://arxiv.org/pdf/2305.14815.pdf}, code={https://github.com/dungtn/cbr-txt} }