publications

2026

2025

1. NeurIPS

   AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

   Dhruv Agarwal, Bodhisattwa Prasad Majumder, Reece Adamson, Megha Chakravorty, Satvika Reddy Gavireddy, Aditya Parashar, Harshit Surana, Bhavana Dalvi Mishra, Andrew McCallum, Ashish Sabharwal, and Peter Clark

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

   Abs PDF

   The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of large language models (LLMs) in goal-driven settings, relying on human-specified research questions to guide hypothesis generation. However, scientific discovery may be accelerated further by allowing the AI system to drive exploration by its own criteria. The few existing approaches in open-ended ASD select hypotheses based on diversity heuristics or subjective proxies for human interestingness, but the former struggles to meaningfully navigate the typically vast hypothesis space, and the latter suffers from imprecise definitions. This paper presents AutoDiscovery—a method for open-ended ASD that instead drives scientific exploration using Bayesian surprise. Here, we quantify the epistemic shift from the LLM’s prior beliefs about a hypothesis to its posterior beliefs after gathering experimental results. To efficiently explore the space of nested hypotheses, our method employs a Monte Carlo tree search (MCTS) strategy with progressive widening using surprisal as the reward function. We evaluate AutoDiscovery in the setting of data-driven discovery across 21 real-world datasets spanning domains such as biology, economics, finance, and behavioral science. Our results demonstrate that under a fixed budget, AutoDiscovery substantially outperforms competitors by producing 5-29% more discoveries deemed surprising by the LLM. Our human evaluation further reveals that two-thirds of discoveries made by our system are surprising to domain experts as well, suggesting this is an important step towards building open-ended ASD systems.

2. ICLR

   DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

   Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, and Peter Clark

   In The Thirteenth International Conference on Learning Representations, 2025

   Abs PDF

   Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. The benchmark is designed to systematically assess current model capabilities in discovery tasks and provide a useful resource for improving them. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering, by manually deriving discovery workflows from published papers to approximate the real-world challenges faced by researchers, where each task is defined by a dataset, its metadata, and a discovery goal in natural language. We additionally provide 903 synthetic tasks to conduct controlled evaluations on data-driven workflows that are not covered in the manually collected split. Furthermore, our structured formalism of data-driven discovery enables a facet-based evaluation that provides useful insights into different failure modes. We evaluate several popular LLM-based reasoning frameworks using both open and closed LLMs as baselines on DiscoveryBench and find that even the best system scores only 25%. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.

3. ICLR

   Searching for Optimal Solutions with LLMs via Bayesian Optimization

   Dhruv Agarwal, Manoj Ghuhan Arivazhagan, Rajarshi Das, Sandesh Swamy, Sopan Khosla, and Rashmi Gangadharaiah

   In The Thirteenth International Conference on Learning Representations, 2025

   Abs PDF

   Scaling test-time compute to search for optimal solutions is an important step towards building generally-capable language models that can reason. Recent work, however, shows that tasks of varying complexity require distinct search strategies to solve optimally, thus making it challenging to design a one-size-fits-all approach. Prior solutions either attempt to predict task difficulty to select the optimal search strategy, often infeasible in practice, or use a static, pre-defined strategy, e.g., repeated parallel sampling or greedy sequential search, which is sub-optimal. In this work, we argue for an alternative view using the probabilistic framework of Bayesian optimization (BO), where the search strategy is adapted dynamically based on the evolving uncertainty estimates of solutions as search progresses. To this end, we introduce Bayesian-OPRO (BOPRO)––a generalization of a recent method for in-context optimization, which iteratively samples from new proposal distributions by modifying the prompt to the LLM with a subset of its previous generations selected to explore or exploit different parts of the search space. We evaluate our method on word search, molecule optimization, and a joint hypothesis+program search task using a 1-D version of the challenging Abstraction and Reasoning Corpus (1D-ARC). Our results show that BOPRO outperforms all baselines in word search (≥10 points) and molecule optimization (higher quality and 17% fewer invalid molecules), but trails a best-k prompting strategy in program search. Our analysis reveals that despite the ability to balance exploration and exploitation using BOPRO, failure is likely due to the inability of code representation models in distinguishing sequences with low edit-distances.

2024

1. ACL

   Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

   Jiachen Zhao, Wenlong Zhao, Andrew Drozdov, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, and Andrew McCallum

   In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Aug 2024

   Abs PDF

   We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs) exhibit room for improvement. In this paper, we present the discovery that a student model distilled from a few-shot prompted LLM can commonly generalize better than its teacher to unseen examples on such tasks. We find that the student is able to learn a general pattern from the high-quality pseudolabels produced by the teacher during knowledge distillation (KD), and favorably not a general pattern from the low-quality pseudolabels. Leveraging this discovery, we propose a new method, Multistage Collaborative Knowledge Distillation from an LLM (MCKD), for these tasks. MCKD first few-shot prompts an LLM to produce pseudolabels for unlabeled data. Then at each stage of an iterative KD process, a new pair of students is trained on disjoint partitions of the pseudolabeled data, and produces new and improved pseudolabels for their unseen partitions. We conduct extensive experiments on four syntactic and semantic parsing datasets and show the effectiveness of MCKD for low-resource semi-supervised sequence generation. On CRAFT biomedical parsing, for example, 3-stage MCKD with 50 labeled examples outperforms an LLM teacher and vanilla KD by 7.5% and 3.7% parsing F1, respectively, and matches the performance of supervised finetuning with 500 labeled examples.

2. ICML

   Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching

   Rico Angell, and Andrew Mccallum

   In Proceedings of the 41st International Conference on Machine Learning, 21–27 jul 2024

   Abs PDF

   While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However, these methods achieve scalability at the cost of an increase in the number of necessary iterations, resulting in slower convergence as the problem size grows. Furthermore, they require iteration-dependent parameter schedules that prohibit effective utilization of warm-start initializations important in practical applications with incrementally-arriving data or mixed-integer programming. We present Unified Spectral Bundling with Sketching (USBS), a provably correct, fast and scalable algorithm for solving massive SDPs that can leverage a warm-start initialization to further accelerate convergence. Our proposed algorithm is a spectral bundle method for solving general SDPs containing both equality and inequality constraints. Moveover, when augmented with an optional matrix sketching technique, our algorithm achieves the dramatically improved scalability of previous work while sustaining convergence speed. We empirically demonstrate the effectiveness of our method across multiple applications, with and without warm-starting. For example, USBS provides a 500x speed-up over the state-of-the-art scalable SDP solver on an instance with over 2 billion decision variables. We make our implementation in pure JAX publicly available.

3. ICML

   Position: Data-driven Discovery with Large Generative Models

   Bodhisattwa Prasad Majumder*, Harshit Surana*, Dhruv Agarwal*, Sanchaita Hazra, Ashish Sabharwal, and Peter Clark

   In Forty-first International Conference on Machine Learning, 21–27 jul 2024

   Abs PDF

   With the accumulation of data at an unprecedented rate, its potential to fuel scientific discovery is growing exponentially. This position paper urges the Machine Learning (ML) community to exploit the capabilities of large generative models (LGMs) to develop automated systems for end-to-end data-driven discovery—a paradigm encompassing the search and verification of hypotheses purely from a set of provided datasets, without the need for additional data collection or physical experiments. We first outline several desiderata for an ideal data-driven discovery system. Then, through DataVoyager, a proof-of-concept utilizing GPT-4, we demonstrate how LGMs fulfill several of these desiderata—a feat previously unattainable—while also highlighting important limitations in the current system that open up opportunities for novel ML research. We contend that achieving accurate, reliable, and robust end-to-end discovery systems solely through the current capabilities of LGMs is challenging. We instead advocate for fail-proof tool integration, along with active user moderation through feedback mechanisms, to foster data-driven scientific discoveries with efficiency and reproducibility.

4. NAACL (Findings)

   Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA

   Dhruv Agarwal, Rajarshi Das, Sopan Khosla, and Rashmi Gangadharaiah

   In Findings of the Association for Computational Linguistics: NAACL 2024, Jun 2024

   Abs PDF

   We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day—attributes that are out-of-scope for current KGQA systems. BYOKG draws inspiration from the remarkable ability of humans to comprehend information present in an unseen KG through exploration—starting at random nodes, inspecting the labels of adjacent nodes and edges, and combining them with their prior world knowledge. Exploration in BYOKG leverages an LLM-backed symbolic agent that generates a diverse set of query-program exemplars, which are then used to ground a retrieval-augmented reasoning procedure to synthesize programs for arbitrary questions. BYOKG is effective over both small- and large-scale graphs, showing dramatic gains in zero-shot QA accuracy of 27.89 and 59.88 F1 on GrailQA and MetaQA, respectively. We further find that performance of BYOKG reliably improves with continued exploration as well as improvements in the base LLM, notably outperforming a state-of-the-art fine-tuned model by 7.08 F1 on a sub-sampled zero-shot split of GrailQA. Lastly, we verify our universality claim by evaluating BYOKG on a domain-specific materials science KG and show that it improves zero-shot performance by 46.33 F1.

2023

1. ACL

   Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling

   Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, and Andrew McCallum

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2023

   Abs PDF Code

   Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is almost as efficient as a single BERT model. Multi-CLS BERT uses multiple CLS tokens with a parameterization and objective that encourages their diversity. Thus instead of fine-tuning each BERT model in an ensemble (and running them all at test time), we need only fine-tune our single Multi-CLS BERT model (and run the one model at test time, ensembling just the multiple final CLS embeddings). To test its effectiveness, we build Multi-CLS BERT on top of a state-of-the-art pretraining method for BERT (Aroca-Ouellette and Rudzicz, 2020). In experiments on GLUE and SuperGLUE we show that our Multi-CLS BERT reliably improves both overall accuracy and confidence estimation. When only 100 training samples are available in GLUE, the Multi-CLS BERT_Base model can even outperform the corresponding BERT_Large model. We analyze the behavior of our Multi-CLS BERT, showing that it has many of the same characteristics and behavior as a typical BERT 5-way ensemble, but with nearly 4-times less computation and memory.

2. ACL (Findings)

   Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond

   Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, and Andrew McCallum

   In Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023

   Abs PDF Code

   Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant nowadays? In this study, we discover that the answers to both questions are no. This is because the softmax bottleneck sometimes prevents the LMs from predicting the desired distribution and the pointer networks can be used to break the bottleneck efficiently. Based on the finding, we propose several softmax alternatives by simplifying the pointer networks and accelerating the word-by-word rerankers. In GPT-2, our proposals are significantly better and more efficient than mixture of softmax, a state-of-the-art softmax alternative. In summarization experiments, without very significantly decreasing its training/testing speed, our best method based on T5-Small improves factCC score by 2 points in CNN/DM and XSUM dataset, and improves MAUVE scores by 30% in BookSum paragraph-level dataset.

3. EMNLP (Findings)

   Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition

   Nishant Yadav, Nicholas Monath, Manzil Zaheer, and Andrew McCallum

   In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023

   Abs PDF

   Cross-encoder models, which jointly encode and score a query-item pair, are prohibitively expensive for direct k-nearest neighbor (k-NN) search. Consequently, k-NN search typically employs a fast approximate retrieval (e.g. using BM25 or dual-encoder vectors), followed by reranking with a cross-encoder; however, the retrieval approximation often has detrimental recall regret. This problem is tackled by ANNCUR (Yadav et al., 2022), a recent work that employs a cross-encoder only, making search efficient using a relatively small number of anchor items, and a CUR matrix factorization. While ANNCUR’s one-time selection of anchors tends to approximate the cross-encoder distances on average, doing so forfeits the capacity to accurately estimate distances to items near the query, leading to regret in the crucial end-task: recall of top-k items. In this paper, we propose ADACUR, a method that adaptively, iteratively, and efficiently minimizes the approximation error for the practically important top-k neighbors. It does so by iteratively performing k-NN search using the anchors available so far, then adding these retrieved nearest neighbors to the anchor set for the next round. Empirically, on multiple datasets, in comparison to previous traditional and state-of-the-art methods such as ANNCUR and dual-encoder-based retrieve-and-rerank, our proposed approach ADACUR consistently reduces recall error—by up to 70% on the important k = 1 setting—while using no more compute than its competitors.

4. AISTATS

   Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining

   Nicholas Monath, Manzil Zaheer, Kelsey Allen, and Andrew Mccallum

   In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, 25–27 apr 2023

   Abs PDF

   Dual encoder models are ubiquitous in modern classification and retrieval. Crucial for training such dual encoders is an accurate estimation of gradients from the partition function of the softmax over the large output space; this requires finding negative targets that contribute most significantly (‘hard negatives). Since dual encoder model parameters change during training, the use of traditional static nearest neighbor indexes can be sub-optimal. These static indexes (1) periodically require expensive re-building of the index, which in turn requires (2) expensive re-encoding of all targets using updated model parameters. This paper addresses both of these challenges. First, we introduce an algorithm that uses a tree structure to approximate the softmax with provable bounds and that dynamically maintains the tree. Second, we approximate the effect of a gradient update on target encodings with an efficient Nystrom low-rank approximation. In our empirical study on datasets with over twenty million targets, our approach cuts error by half in relation to oracle brute-force negative mining. Furthermore, our method surpasses prior state-of-the-art while using 150x less accelerator memory.

5. EACL

   Low-Resource Compositional Semantic Parsing with Concept Pretraining

   Subendhu Rongali, Mukund Sridhar, Haidar Khan, Konstantine Arkoudas, Wael Hamza, and Andrew McCallum

   In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023

   Abs PDF

   Semantic parsing plays a key role in digital voice assistants such as Alexa, Siri, and Google Assistant by mapping natural language to structured meaning representations. When we want to improve the capabilities of a voice assistant by adding a new domain, the underlying semantic parsing model needs to be retrained using thousands of annotated examples from the new domain, which is time-consuming and expensive. In this work, we present an architecture to perform such domain adaptation automatically, with only a small amount of metadata about the new domain and without any new training data (zero-shot) or with very few examples (few-shot). We use a base seq2seq (sequence-to-sequence) architecture and augment it with a concept encoder that encodes intent and slot tags from the new domain. We also introduce a novel decoder-focused approach to pretrain seq2seq models to be concept aware using Wikidata and use it to help our model learn important concepts and perform well in low-resource settings. We report few-shot and zero-shot results for compositional semantic parsing on the TOPv2 dataset and show that our model outperforms prior approaches in few-shot settings for the TOPv2 and SNIPS datasets.

6. EMNLP (Findings)

   Machine Reading Comprehension using Case-based Reasoning

   Dung Thai, Dhruv Agarwal, Mudit Chaudhary, Wenlong Zhao, Rajarshi Das, Jay-Yoon Lee, Hannaneh Hajishirzi, Manzil Zaheer, and Andrew McCallum

   In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023

   Abs PDF

   We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our method (CBR-MRC) builds upon the hypothesis that contextualized answers to similar questions share semantic similarities with each other. Given a test question, CBR-MRC first retrieves a set of similar cases from a nonparametric memory and then predicts an answer by selecting the span in the test context that is most similar to the contextualized representations of answers in the retrieved cases. The semi-parametric nature of our approach allows it to attribute a prediction to the specific set of evidence cases, making it a desirable choice for building reliable and debuggable QA systems. We show that CBR-MRC provides high accuracy comparable with large reader models and outperforms baselines by 11.5 and 8.4 EM on NaturalQuestions and NewsQA, respectively. Further, we demonstrate the ability of CBR-MRC in identifying not just the correct answer tokens but also the span with the most relevant supporting evidence. Lastly, we observe that contexts for certain question types show higher lexical diversity than others and find that CBR-MRC is robust to these variations while performance using fully-parametric methods drops.

7. ACL (Findings)

   Causal Matching with Text Embeddings: A Case Study in Estimating the Causal Effects of Peer Review Policies

   Raymond Zhang, Neha Nayak Kennard, Daniel Smith, Daniel McFarland, Andrew McCallum, and Katherine Keith

   In Findings of the Association for Computational Linguistics: ACL 2023, Jul 2023

   Abs PDF

   A promising approach to estimate the causal effects of peer review policies is to analyze data from publication venues that shift policies from single-blind to double-blind from one year to the next. However, in these settings the content of the manuscript is a confounding variable—each year has a different distribution of scientific content which may naturally affect the distribution of reviewer scores. To address this textual confounding, we extend variable ratio nearest neighbor matching to incorporate text embeddings. We compare this matching method to a widely-used causal method of stratified propensity score matching and a baseline of randomly selected matches. For our case study of the ICLR conference shifting from single- to double-blind review from 2017 to 2018, we find human judges prefer manuscript matches from our method in 70% of cases. While the unadjusted estimate of the average causal effect of reviewers’ scores is -0.25, our method shifts the estimate to -0.17, a slightly smaller difference between the outcomes of single- and double-blind policies. We hope this case study enables exploration of additional text-based causal estimation methods and domains in the future.

8. SIGIR

   Editable User Profiles for Controllable Text Recommendations

   Sheshera Mysore, Mahmood Jasim, Andrew Mccallum, and Hamed Zamani

   In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2023

   Abs PDF

   Methods for making high-quality recommendations often rely on learning latent representations from interaction data. These methods, while performant, do not provide ready mechanisms for users to control the recommendation they receive. Our work tackles this problem by proposing LACE, a novel concept value bottleneck model for controllable text recommendations. LACE represents each user with a succinct set of human-readable concepts through retrieval given user-interacted documents and learns personalized representations of the concepts based on user documents. This concept based user profile is then leveraged to make recommendations. The design of our model affords control over the recommendations through a number of intuitive interactions with a transparent user profile. We first establish the quality of recommendations obtained from LACE in an offline evaluation on three recommendation tasks spanning six datasets in warm-start, cold-start, and zero-shot setups. Next, we validate the controllability of LACE under simulated user interactions. Finally, we implement LACE in an interactive controllable recommender system and conduct a user study to demonstrate that users are able to improve the quality of recommendations they receive through interactions with an editable user profile.

9. KDD

   Online Level-wise Hierarchical Clustering

   Nicholas Monath, Manzil Zaheer, and Andrew McCallum

   In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Jul 2023

   Abs PDF

   Online hierarchical clustering algorithms, compared to their scalable batch setting counterparts, typically provide more limited accuracy and efficiency performance. Yet, when data is incrementally arriving, a crucial setting in many clustering applications (e.g., entity resolution and concept discovery), these batch setting algorithms do not apply. This paper presents a family of new algorithms for online hierarchical clustering that combine high quality trees and fast per-point insertion time–made possible through a limited number of parallel non-greedy tree re-arrangements. We analyze our methods under assumptions about the data and the separability of clusters. Empirically, we find that our proposed algorithms yield state-of-the-art results in hierarchical clustering dendrogram purity and in building compressed prototypes for a k-nearest representative classifier.

10. RecSys

    Large Language Model Augmented Narrative Driven Recommendations

    Sheshera Mysore, Andrew Mccallum, and Hamed Zamani

    In Proceedings of the 17th ACM Conference on Recommender Systems, Jul 2023

    Abs PDF

    Narrative-driven recommendation (NDR) presents an information access problem where users solicit recommendations with verbose descriptions of their preferences and context, for example, travelers soliciting recommendations for points of interest while describing their likes/dislikes and travel circumstances. These requests are increasingly important with the rise of natural language-based conversational interfaces for search and recommendation systems. However, NDR lacks abundant training data for models, and current platforms commonly do not support these requests. Fortunately, classical user-item interaction datasets contain rich textual data, e.g., reviews, which often describe user preferences and context – this may be used to bootstrap training for NDR models. In this work, we explore using large language models (LLMs) for data augmentation to train NDR models. We use LLMs for authoring synthetic narrative queries from user-item interactions with few-shot prompting and train retrieval models for NDR on synthetic queries and user-item interaction data. Our experiments demonstrate that this is an effective strategy for training small-parameter retrieval models that outperform other retrieval and LLM baselines for narrative-driven recommendation.

11. EMNLP (Findings)

    PaRaDe: Passage Ranking using Demonstrations with LLMs

    Andrew Drozdov, Honglei Zhuang, Zhuyun Dai, Zhen Qin, Razieh Rahimi, Xuanhui Wang, Dana Alon, Mohit Iyyer, Andrew McCallum, Donald Metzler, and Kai Hui

    In Findings of the Association for Computational Linguistics: EMNLP 2023, Dec 2023

    Abs PDF

    Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method, such as BM25, are rated and reordered to improve relevance. In this work, we improve LLM-based re-ranking by algorithmically selecting few-shot demonstrations to include in the prompt. Our analysis investigates the conditions where demonstrations are most helpful, and shows that adding even one demonstration is significantly beneficial. We propose a novel demonstration selection strategy based on difficulty rather than the commonly used semantic similarity. Furthermore, we find that demonstrations helpful for ranking are also effective at question generation. We hope our work will spur more principled research into question generation and passage ranking.

2022

1. NAACL

   Inducing and Using Alignments for Transition-based AMR Parsing

   Andrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, and Ramon Fernandez Astudillo

   In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Dec 2022

   PDF
2. EMNLP (Findings)

   You can’t pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LM

   Andrew Drozdov, Shufan Wang, Razieh Rahimi, Andrew McCallum, Hamed Zamani, and Mohit Iyyer

   In Findings of the Association for Computational Linguistics: EMNLP 2022, Dec 2022

   PDF
3. NAACL

   DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions

   Neha Kennard, Tim O’Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, and Andrew McCallum

   In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Dec 2022
4. ICML

   Knowledge base question answering by case-based reasoning over subgraphs

   Rajarshi Das, Ameya Godbole, Ankita Naik, Elliot Tower, Manzil Zaheer, Hannaneh Hajishirzi, Robin Jia, and Andrew McCallum

   In International Conference on Machine Learning (ICML), Dec 2022
5. NAACL

   Entity Linking via Explicit Mention-Mention Coreference Modeling

   Dhruv Agarwal, Rico Angell, Nicholas Monath, and Andrew McCallum

   In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jul 2022

   Abs PDF

   Learning representations of entity mentions is a core component of modern entity linking systems for both candidate generation and making linking predictions. In this paper, we present and empirically analyze a novel training approach for learning mention and entity representations that is based on building minimum spanning arborescences (i.e., directed spanning trees) over mentions and entities across documents to explicitly model mention coreference relationships. We demonstrate the efficacy of our approach by showing significant improvements in both candidate generation recall and linking accuracy on the Zero-Shot Entity Linking dataset and MedMentions, the largest publicly available biomedical dataset. In addition, we show that our improvements in candidate generation yield higher quality re-ranking models downstream, setting a new SOTA result in linking accuracy on MedMentions. Finally, we demonstrate that our improved mention representations are also effective for the discovery of new entities via cross-document coreference.

6. ICML

   Interactive Correlation Clustering with Existential Cluster Constraints

   Rico Angell, Nicholas Monath, Nishant Yadav, and Andrew McCallum

   In International Conference on Machine Learning (ICML), Jul 2022
7. AAAI

   An Evaluative Measure of Clustering Methods Incorporating Hyperparameter Sensitivity

   Siddhartha Mishra, Nicholas Monath, Michael Boratko, Ariel Kobren, and Andrew McCallum

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Jul 2022
8. AAAI

   Sublinear Time Approximation of Text Similarity Matrices

   Archan Ray, Nicholas Monath, Andrew McCallum, and Cameron Musco

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Jul 2022
9. ACL

   Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions

   Haw-Shiuan Chang, and Andrew McCallum

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2022
10. ACL

    Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings

    Shib Dasgupta, Michael Boratko, Siddhartha Mishra, Shriya Atmakuri, Dhruvesh Patel, Xiang Li, and Andrew McCallum

    In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2022
11. ICLR

    Modeling label space interactions in multi-label classification using box embeddings

    Dhruvesh Patel, Pavitra Dangati, Jay-Yoon Lee, Michael Boratko, and Andrew McCallum

    In International Conference on Learning Representations (ICLR), Jul 2022
12. EMNLP

    Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization

    Nishant Yadav, Nicholas Monath, Rico Angell, Manzil Zaheer, and Andrew McCallum

    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), Jul 2022

    Code
13. NeurIPS

    Structured energy network as a loss

    Jay Yoon Lee, Dhruvesh Patel, Purujit Goyal, Wenlong Zhao, Zhiyang Xu, and Andrew McCallum

    Advances in Neural Information Processing Systems, Jul 2022

    PDF

2021

1. Improved Latent Tree Induction with Distant Supervision via Span Constraints

   Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O’Gorman, Subendhu Rongali, Dylan Finkbeiner, Shilpa Suresh, Mohit Iyyer, and Andrew McCallum

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Jul 2021
2. Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

   Haw-Shiuan Chang, Amol Agrawal, and Andrew McCallum

   In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Jul 2021

   Poster Slides
3. Changing the Mind of Transformers for Topically-Controllable Language Generation

   Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer, and Andrew McCallum

   In Conference of the European Chapter of the Association for Computational Linguistics (EACL), Jul 2021

   Code Video Poster Slides
4. Multi-facet Universal Schema

   Rohan Paul*, Haw-Shiuan Chang*, and Andrew McCallum

   In Conference of the European Chapter of the Association for Computational Linguistics (EACL), Jul 2021

   Code Video Poster Slides
5. MS-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural Text

   Tim O’Gorman, Zach Jensen, Sheshera Mysore, Kevin Huang, Rubayyat Mahbub, Elsa Olivetti, and Andrew McCallum

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021
6. CSFCube - A Test Collection of Computer Science Research Articles for Faceted Query by Example

   Sheshera Mysore, Tim O’Gorman, Andrew McCallum, and Hamed Zamani

   In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), Nov 2021

   Code
7. Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity

   Sheshera Mysore, Arman Cohan, and Tom Hope

   CoRR, Nov 2021

   Code
8. Clustering-based Inference for Biomedical Entity Linking

   Rico Angell, Nicholas Monath, Sunil Mohan, Nishant Yadav, and Andrew McCallum

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Nov 2021
9. Event and Entity Coreference using Trees to Encode Uncertainty in Joint Decisions

   Nishant Yadav, Nicholas Monath, Rico Angell, and Andrew McCallum

   In Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference at EMNLP, Nov 2021
10. SUBSUME: A Dataset for Subjective Summary Extraction from Wikipedia Documents

    Nishant Yadav*, Matteo Brucato*, Anna Fariha*, Oscar Youngquist, Julian Killingback, Alexandra Meliou, and Peter Haas

    In Proceedings of the Third Workshop on New Frontiers in Summarization at EMNLP, Nov 2021
11. EMNLP

    Case-based Reasoning for Natural Language Queries over Knowledge Bases

    Rajarshi Das, Manzil Zaheer, Dung Thai, Ameya Godbole, Ethan Perez, Jay Yoon Lee, Lizhen Tan, Lazaros Polymenakos, and Andrew McCallum

    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2021
12. Simultaneously self-attending to text and entities for knowledge-informed text representations

    Dung Thai, Raghuveer Thirukovalluru, Trapit Bansal, and Andrew McCallum

    In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), Nov 2021
13. EMNLP

    Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP

    Trapit Bansal, Karthick Prasad Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, and Andrew McCallum

    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2021
14. NeurIPS

    Capacity and Bias of Learned Geometric Embeddings for Directed Graphs

    Michael Boratko, Dongxu Zhang, Nicholas Monath, Luke Vilnis, Kenneth L Clarkson, and Andrew McCallum

    Advances in Neural Information Processing Systems (NeurIPS), Nov 2021
15. UAI

    Exact and approximate hierarchical clustering using A*

    Craig S Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty, Manzil Zaheer, Amr Ahmed, Kyle Cranmer, and Andrew McCallum

    In Uncertainty in Artificial Intelligence (UAI), Nov 2021
16. KDD

    Scalable Hierarchical Agglomerative Clustering

    Nicholas Monath, Kumar Avinava Dubey, Guru Guruganesh, Manzil Zaheer, Amr Ahmed, Andrew McCallum, Gokhan Mergen, Marc Najork, Mert Terzihan, Bryon Tjanaka, and  others

    In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD), Nov 2021
17. ACL

    Scaling within document coreference to long texts

    Raghuveer Thirukovalluru, Nicholas Monath, Kumar Shridhar, Manzil Zaheer, Mrinmaya Sachan, and Andrew McCallum

    In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (ACL), Nov 2021
18. AISTATS

    Dag-structured clustering by nearest neighbors

    Nicholas Monath, Manzil Zaheer, Kumar Avinava Dubey, Amr Ahmed, and Andrew McCallum

    In International Conference on Artificial Intelligence and Statistics (AISTATS), Nov 2021
19. AISTATS

    Cluster trellis: Data structures & algorithms for exact inference in hierarchical clustering

    Sebastian Macaluso, Craig Greenberg, Nicholas Monath, Ji Ah Lee, Patrick Flaherty, Kyle Cranmer, Andrew McGregor, and Andrew McCallum

    In International Conference on Artificial Intelligence and Statistics (AISTATS), Nov 2021
20. Box-to-box transformations for modeling joint hierarchies

    Shib Sankar Dasgupta, Xiang Lorraine Li, Michael Boratko, Dongxu Zhang, and Andrew McCallum

    In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), Nov 2021
21. NAACL

    Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning

    Xuelu Chen, Michael Boratko, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li, and Andrew McCallum

    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Nov 2021
22. UAI

    Min/max stability and box distributions

    Michael Boratko, Javier Burroni, Shib Sankar Dasgupta, and Andrew McCallum

    In Uncertainty in Artificial Intelligence (UAI), Nov 2021

2020

1. Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition

   Haw-Shiuan Chang, Shankar Vembu, Sunil Mohan, Rheeya Uppaal, and Andrew McCallum

   Machine Learning, Nov 2020

   Video Slides
2. Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders

   Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O’Gorman, Mohit Iyyer, and Andrew McCallum

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020
3. Unsupervised Pre-training for Biomedical Question Answering

   Vaishnavi Kommaraju, Karthick Gunasekaran, Kun Li, Trapit Bansal, Andrew McCallum, Ivana Williams, and Ana-Maria Istrate

   In CLEF (Working Notes), Nov 2020
4. Simultaneously linking entities and extracting relations from biomedical text without mention-level supervision

   Trapit Bansal, Pat Verga, Neha Choudhary, and Andrew McCallum

   In Proceedings of the AAAI Conference on Artificial Intelligence, Nov 2020
5. Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks

   Trapit Bansal, Rishikesh Jha, and Andrew McCallum

   In Proceedings of the 28th International Conference on Computational Linguistics, Nov 2020
6. Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks

   Trapit Bansal, Rishikesh Jha, Tsendsuren Munkhdalai, and Andrew McCallum

   In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020
7. An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text

   Daivik Swarup, Ahsaas Bajaj, Sheshera Mysore, Tim O’Gorman, Rajarshi Das, and Andrew McCallum

   In Findings of the Association for Computational Linguistics: EMNLP 2020, Nov 2020
8. EMNLP

   Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion

   Rajarshi Das, Ameya Godbole, Nicholas Monath, Manzil Zaheer, and Andrew McCallum

   In Findings of the Association for Computational Linguistics: EMNLP 2020 (EMNLP), Nov 2020
9. AKBC

   A Simple Approach to Case-Based Reasoning in Knowledge Bases

   Rajarshi Das, Ameya Godbole, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum

   In Automated Knowledge Base Construction (AKBC), Nov 2020
10. EMNLP

    ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning

    Michael Boratko, Xiang Li, Tim O’Gorman, Rajarshi Das, Dan Le, and Andrew McCallum

    In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2020
11. AKBC

    Using BibTeX to Automatically Generate Labeled Data for Citation Field Extraction

    Dung Thai, Zhiyang Xu, Nicholas Monath, Boris Veytsman, and Andrew McCallum

    In Automated Knowledge Base Construction (AKBC), Nov 2020
12. AKBC

    Predicting Institution Hierarchies with Set-based Models

    Derek Tam, Nicholas Monath, Ari Kobren, and Andrew McCallum

    In Automated Knowledge Base Construction (AKBC), Nov 2020
13. NeurIPS

    Improving local identifiability in probabilistic box embeddings

    Shib Dasgupta, Michael Boratko, Dongxu Zhang, Luke Vilnis, Xiang Li, and Andrew McCallum

    Advances in Neural Information Processing Systems (NeurIPS), Nov 2020
14. AKBC

    Representing Joint Hierarchies with Box Embeddings

    Dhruvesh Patel, Shib Sankar Dasgupta, Michael Boratko, Xiang Li, Luke Vilnis, and Andrew McCallum

    In Conference on Automated Knowledge Base Construction, AKBC 2020, Virtual, June 22-24, 2020 (AKBC), Nov 2020

2019

1. Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

   Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum

   In International Conference on Learning Representations (ICLR), Nov 2019
2. Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

   Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum

   In International Conference on Learning Representations (ICLR), Nov 2019
3. Smoothing the Geometry of Box Embeddings

   Xiang Li, Luke Vilnis, Dongxu Zhang, Michael Boratko, and Andrew McCallum

   In International Conference on Learning Representations (ICLR), Nov 2019
4. OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference

   Dongxu Zhang, Subhabrata Mukherjee, Colin Lockard, Luna Dong, and Andrew McCallum

   In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Nov 2019
5. Supervised Hierarchical Clustering with Exponential Linkage

   Nishant Yadav, Ari Kobren, Nicholas Monath, and Andrew McCallum

   In International Conference on Machine Learning (ICML), Nov 2019

   Code
6. Integrating User Feedback under Identity Uncertainty in Knowledge Base Construction

   Ari Kobren, Nicholas Monath, and Andrew McCallum

   In Automated Knowledge Base Construction (AKBC), Nov 2019
7. Optimal Transport-based Alignment of Learned Character Representations for String Similarity

   Derek Tam, Nicholas Monath, Ari Kobren, Aaron Traylor, Rajarshi Das, and Andrew McCallum

   In Association of Computational Linguistics (ACL), Nov 2019
8. Scalable Hierarchical Clustering with Tree Grafting

   Nicholas Monath*, Ari Kobren*, Akshay Krishnamurthy, Michael Glass, and Andrew McCallum

   In International Conference on Knowledge Discovery and Data Mining (KDD), Nov 2019
9. Paper Matching with Local Fairness Constraints

   Ari Kobren, Barna Saha, and Andrew McCallum

   In International Conference on Knowledge Discovery and Data Mining (KDD), Nov 2019

   Code
10. Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space

    Nicholas Monath, Manzil Zaheer, Daniel Silva, Andrew McCallum, and Amr Ahmed

    In International Conference on Knowledge Discovery and Data Mining (KDD), Nov 2019
11. The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures

    Sheshera Mysore, Zach Jensen, Edward Kim, Kevin Huang, Haw-Shiuan Chang, Emma Strubell, Jeffrey Flanigan, Andrew McCallum, and Elsa Olivetti

    In Proceedings of the 13th Linguistic Annotation Workshop at ACL, Nov 2019
12. A2N: Attending to Neighbors for Knowledge Graph Inference

    Trapit Bansal, Da-Cheng Juan, Sujith Ravi, and Andrew McCallum

    In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Jul 2019
13. Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders

    Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer, and Andrew McCallum

    In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), Jul 2019
14. Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders

    Andrew Drozdov, Patrick Verga, Yi-Pei Chen, Mohit Iyyer, and Andrew McCallum

    In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), Jul 2019
15. Chains-of-reasoning at textgraphs 2019 shared task: Reasoning over chains of facts for explainable multi-hop inference

    Rajarshi Das, Ameya Godbole, Manzil Zaheer, Shehzaad Dhuliawala, and Andrew McCallum

    In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), Jul 2019
16. Multi-step entity-centric information retrieval for multi-hop question answering

    Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, and  others

    In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, Jul 2019

2018

1. Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection

   Haw-Shiuan Chang, ZiYun Wang, Luke Vilnis, and Andrew McCallum

   In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Jul 2018

   Code Poster
2. Simultaneously Self-attending to All Mentions for Full-Abstract Biological Relation Extraction

   Patrick Verga, Emma Strubell, and Andrew McCallum

   In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Jul 2018

   Code
3. Training Structured Prediction Energy Networks with Indirect Supervision

   Amirmohammad Rooshenas, Aishwarya Kamath, and Andrew McCallum

   In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), Jul 2018
4. Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings

   Haw-Shiuan Chang, Amol Agrawal, Ananya Ganesh, Anirudha Desai, Vinayak Mathur, Alfred Hough, and Andrew McCallum

   In TextGraphs-12: the Workshop on Graph-based Methods for Natural Language Processing (NAACL WS), Jul 2018

   Slides
5. Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking

   Shikhar Murty*, Patrick Verga*, Luke Vilnis, Irena Radovanovic, and Andrew McCallum (* Equal Contribution)

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2018
6. Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures

   Luke Vilnis*, Xiang Li*, Shikhar Murty, and Andrew McCallum (* Equal Contribution)

   In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), Jul 2018
7. Compact Representation of Uncertainty in Clustering

   Craig Greenberg, Nicholas Monath, Ari Kobren, Patrick Flaherty, Andrew McGregor, and Andrew McCallum

   In Advances in Neural Information Processing Systems (NIPS), Jul 2018
8. Embedded-State Latent Conditional Random Fields for Sequence Labeling

   Dung Thai, Sree Harsha Ramesh, Shikhar Murty, Luke Vilnis, and Andrew McCallum

   In Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL), Jul 2018
9. Linguistically-Informed Self-Attention for Semantic Role Labeling

   Emma Strubell, Patrick Verga, Daniel Andor, David Weiss, and Andrew McCallum

   In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Jul 2018
10. Marginal Likelihood Training of BiLSTM-CRF for Biomedical Named Entity Recognition from Disjoint Label Sets

    Nathan Greenberg, Trapit Bansal, Patrick Verga, and Andrew McCallum

    In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), Jul 2018
11. Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning

    Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum

    In International Conference on Learning Representations (ICLR), Jul 2018

    Code
12. A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset

    Michael Boratko, Harshit Padigela, Divyendra Mikkilineni, Pritish Yuvraj, Rajarshi Das, Andrew McCallum, Maria Chang, Achille Fokoue-Nkoutche, Pavan Kapanipathi, Nicholas Mattei, and  others

    In Proceedings of the Workshop on Machine Reading for Question Answering, Jul 2018

2017

1. Learning a Natural Language Interface with Neural Programmer

   Arvind Neelakantan, Quoc V. Le, Martin Abadi, Andrew McCallum, and Dario Amodei

   In International Conference on Learning Representations (ICLR), Jul 2017
2. Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema

   Patrick Verga, Arvind Neelakantan, and Andrew McCallum

   In 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, Jul 2017
3. Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks

   Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum

   In 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, Jul 2017

   Slides
4. A Hierarchical Algorithm for Extreme Clustering

   Ari Kobren, Nicholas Monath, Akshay Krishnamurthy, and Andrew McCallum

   In Proceedings of the 23rd ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Halifax, NS, Canada, August 13 - 17, 2017, Jul 2017

   Code Video
5. End-to-End Learning for Structured Prediction Energy Networks

   David Belanger, Bishan Yang, and Andrew McCallum

   In Proceedings of the 34th International Conference on Machine Learning (ICML), Sydney, NSW, Australia, 6-11 August 2017, Jul 2017
6. Dependency Parsing with Dilated Iterated Graph CNNs

   Emma Strubell, and Andrew McCallum

   In Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing (SPNLP at EMNLP), Copenhagen, Denmark, September 2017, Jul 2017
7. Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

   Emma Strubell, Patrick Verga, David Belanger, and Andrew McCallum

   In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), Copenhagen, Denmark, September 9-11, 2017, Jul 2017

   Code
8. Active Bias: Training a More Accurate Neural Network by Emphasizing High Variance Samples

   Haw-Shiuan Chang, Erik G. Learned-Miller, and Andrew McCallum

   In Advances in Neural Information Processing Systems (NIPS), Jul 2017

   Poster
9. SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

   Isabelle Augenstein, Mrinal Das, Sebastian Riedel, Lakshmi Vikraman, and Andrew McCallum

   In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval at ACL), Vancouver, Canada, August 3-4, 2017, Jul 2017
10. Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks

    Rajarshi Das, Manzil Zaheer, Siva Reddy, and Andrew McCallum

    In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Vancouver, Canada, July 30 - August 4, Volume 2: Short Papers, Jul 2017
11. RelNet: End-to-end Modeling of Entities & Relations

    Trapit Bansal, Arvind Neelakantan, and Andrew McCallum

    arXiv preprint, Jul 2017
12. Low-Rank Hidden State Embeddings for Viterbi Sequence Labeling

    Dung Thai, Shikhar Murty, Trapit Bansal, Luke Vilnis, David Belanger, and Andrew McCallum

    In International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS), Jul 2017
13. Improved Representation Learning for Predicting Commonsense Ontologies

    Xiang Li, Luke Vilnis, and Andrew McCallum

    In International Conference on Machine Learning Workshop on Deep Structured Prediction (ICML WS), Jul 2017
14. Learning String Alignments for Entity Aliases

    Aaron Traylor, Nicholas Monath, Rajarshi Das, and Andrew McCallum

    In 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS, Jul 2017

    Code
15. Entity-centric Attribute Feedback for Interactive Knowledge Bases

    Ari Kobren, Nicholas Monath, and Andrew McCallum

    In 6th Workshop on Automated Knowledge Base Construction (AKBC) 2017 at NIPS, Jul 2017
16. Gradient-based Hierarchical Clustering

    Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, and Andrew McCallum

    In NIPS Workshop on Discrete Structures in Machine Learning (DISCML), Jul 2017
17. Automatically Extracting Action Graphs from Materials Science Synthesis Procedures

    Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, and Elsa Olivetti

    In Workshop on Machine Learning for Molecules and Materials at NIPS, Jul 2017

2016

1. Structured Prediction Energy Networks

   David Belanger, and Andrew McCallum

   In Proceedings of the 33rd International Conference on Machine Learning (ICML), New York City, NY, USA, June 19-24, 2016, Jul 2016
2. Row-less Universal Schema

   Patrick Verga, and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016, Jul 2016
3. Multilingual Relation Extraction using Compositional Universal Schema

   Patrick Verga, David Belanger, Emma Strubell, Benjamin Roth, and Andrew McCallum

   In 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, Jul 2016

   Code
4. Incorporating Selectional Preferences in Multi-hop Relation Extraction

   Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016, Jul 2016
5. Call for Discussion: Building a New Standard Dataset for Relation Extraction Tasks

   Teresa Martin, Fiete Botschen, Ajay Nagesh, and Andrew McCallum

   In Proceedings of the 5th Workshop on Automated Knowledge Base Construction (AKBC at NAACL-HLT), San Diego, CA, USA, June 17, 2016, Jul 2016
6. Ask the GRU: Multi-task Learning for Deep Text Recommendations

   Trapit Bansal, David Belanger, and Andrew McCallum

   In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys), Boston, MA, USA, September 15-19, 2016, Jul 2016
7. Extracting Multilingual Relations under Limited Resources: TAC 2016 Cold-Start KB construction and Slot-Filling using Compositional Universal Schema

   Haw-Shiuan Chang, Abdurrahman Munir, Ao Liu, Johnny Tian-Zheng Wei, Aaron Traylor, Ajay Nagesh, Nicholas Monath, Patrick Verga, Emma Strubell, and Andrew McCallum

   In Text Analysis Conference, Knowledge Base Population (TAC/KBP), Jul 2016

2015

1. Word Representations via Gaussian Embedding

   Luke Vilnis, and Andrew McCallum

   In International Conference on Learning Representations (ICLR), Jul 2015
2. Embedded Representations of Lexical and Knowledge-Base Semantics

   Andrew McCallum

   In Proceedings of the 2015 International Conference on The Theory of Information Retrieval (ICTIR), Northampton, Massachusetts, USA, September 27-30, 2015, Jul 2015
3. Compositional Vector Space Models for Knowledge Base Completion

   Arvind Neelakantan, Benjamin Roth, and Andrew McCallum

   In 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, Jul 2015
4. Learning Dynamic Feature Selection for Fast Sequential Prediction

   Emma Strubell, Luke Vilnis, Kate Silverstein, and Andrew McCallum

   In 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, Jul 2015
5. Bethe Projections for Non-Local Inference

   Luke Vilnis, David Belanger, Daniel Sheldon, and Andrew McCallum

   In Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence (UAI), July 12-16, 2015, Amsterdam, The Netherlands, Jul 2015
6. Reports on the 2015 AAAI Spring Symposium Series

   Nitin Agarwal, Sean Andrist, Dan Bohus, Fei Fang, Laurie Fenstermacher, Lalana Kagal, Takashi Kido, Christopher Kiekintveld, William F. Lawless, Huan Liu, Andrew McCallum, Hemant Purohit, Oshani Seneviratne, Keiki Takadama, and Gavin Taylor

   AI Magazine, Jul 2015
7. Building Knowledge Bases with Universal Schema: Cold Start and Slot-Filling Approaches

   Benjamin Roth, Nicholas Monath, David Belanger, Emma Strubell, Patrick Verga, and Andrew McCallum

   In Text Analysis Conference, Knowledge Base Population (TAC/KBP), Jul 2015
8. Compositional Vector Space Models for Knowledge Base Inference

   Arvind Neelakantan, Benjamin Roth, and Andrew McCallum

   In AAAI Spring Symposium Series (AAAI-SS), Jul 2015
9. Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches

   Evgeniy Gabrilovich, Ramanathan Guha, Andrew McCallum, and Kevin Murphy

   In AAAI Spring Symposium Series (AAAI-SS), Jul 2015

2014

1. Lexicon Infused Phrase Embeddings for Named Entity Resolution

   Alexandre Passos, Vineet Kumar, and Andrew McCallum

   In Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL), Baltimore, Maryland, USA, June 26-27, 2014, Jul 2014
2. Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space

   Arvind Neelakantan, Jeevan Shankar, Alexandre Passos, and Andrew McCallum

   In 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, Jul 2014
3. Message Passing for Soft Constraint Dual Decomposition

   David Belanger, Alexandre Passos, Sebastian Riedel, and Andrew McCallum

   In Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence (UAI), Quebec City, Quebec, Canada, July 23-27, 2014, Jul 2014
4. Learning Soft Linear Constraints with Application to Citation Field Extraction

   Sam Anzaroot, Alexandre Passos, David Belanger, and Andrew McCallum

   In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL), June 22-27, 2014, Baltimore, MD, USA, Volume 1: Long Papers, Jul 2014
5. Universal Schema for Slot-Filling, Cold-Start KBP and Event Argument Extraction: UMass IESL at TAC KBP 2014

   Benjamin Roth, Emma Strubell, John Sullivan, Lakshmi Vikraman, Katherine Silverstein, and  Andrew McCallum

   In Text Analysis Conference, Knowledge Base Population (TAC/KBP), Jul 2014
6. Training for Fast Sequential Prediction Using Dynamic Feature Selection

   Emma Strubell, Luke Vilnis, and  Andrew McCallum

   In NIPS Workshop on Modern Machine Learning and NLP (NIPS WS), Jul 2014
7. Knowledge Base Completion using Compositional Vector Space Models

   Arvind Neelakantan, Benjamin Roth, and Andrew McCallum

   In 4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS, Jul 2014
8. Minimally Supervised Event Argument Extraction using Universal Schema

   Benjamin Roth, Emma Strubell, Katherine Silverstein, and Andrew McCallum

   In 4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS, Jul 2014
9. A Hierarchical Model for Universal Schema Relation Extraction

   Arvind Neelakantan, Alexandre Passos, and Andrew McCallum

   In 4th Workshop on Automated Knowledge Base Construction (AKBC) 2014 at NIPS, Jul 2014

2013

1. Dynamic Knowledge-Base Alignment for Coreference Resolution

   Jiaping Zheng, Luke Vilnis, Sameer Singh, Jinho D. Choi, and Andrew McCallum

   In Proceedings of the Seventeenth Conference on Computational Natural Language Learning (CoNLL), Sofia, Bulgaria, August 8-9, 2013, Jul 2013
2. Transition-based Dependency Parsing with Selectional Branching

   Jinho D. Choi, and Andrew McCallum

   In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL), 4-9 August 2013, Sofia, Bulgaria, Volume 1: Long Papers, Jul 2013
3. Universal schema for entity type prediction

   Limin Yao, Sebastian Riedel, and Andrew McCallum

   In Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013, Jul 2013
4. Assessing confidence of knowledge base content with an experimental study in entity resolution

   Michael L. Wick, Sameer Singh, Ari Kobren, and Andrew McCallum

   In Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013, Jul 2013
5. A joint model for discovering and linking entities

   Michael L. Wick, Sameer Singh, Harshal Pandya, and Andrew McCallum

   In Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013, Jul 2013
6. Universal Schema for Slot Filling and Cold Start: UMass IESL at TACKBP 2013

   Sameer Singh, Limin Yao, David Belanger, Ari Kobren, Sam Anzaroot, Mike Wick, Alexandre Passos, Harshal Pandya, Jinho D. Choi, Brian Martin, and Andrew McCallum

   In Proceedings of the Sixth Text Analysis Conference, (TAC), Gaithersburg, Maryland, USA, November 18-19, 2013, Jul 2013
7. Joint inference of entities, relations, and coreference

   Sameer Singh, Sebastian Riedel, Brian Martin, Jiaping Zheng, and Andrew McCallum

   In Proceedings of the 2013 workshop on Automated knowledge base construction (AKBC at CIKM), San Francisco, California, USA, October 27-28, 2013, Jul 2013
8. Latent Relation Representations for Universal Schemas

   Sebastian Riedel, Limin Yao, and Andrew McCallum

   In International Conference on Learning Representations (ICLR), Jul 2013
9. Relation Extraction with Matrix Factorization and Universal Schemas

   Sebastian Riedel, Limin Yao, Andrew McCallum, and Benjamin M. Marlin

   In 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, Jul 2013
10. Open Scholarship and Peer Review: a Time for Experimentation

    David Soergel, Adam Saunders, and Andrew McCallum

    In ICML Workshop on Peer Reviewing and Publishing Models (PEER), Jul 2013
11. A New Dataset for Fine-Grained Citation Field Extraction

    Sam Anzaroot, and Andrew McCallum

    In ICML Workshop on Peer Reviewing and Publishing Models (PEER), Jul 2013
12. Large-scale Author Coreference via Hierarchical Entity Representations

    Michael L Wick, Ari Kobren, and Andrew McCallum

    In ICML Workshop on Peer Reviewing and Publishing Models (PEER), Jul 2013
13. Wikilinks: A Large-scale Cross-Document Coreference Corpus Labeled via Links to Wikipedia

    Sameer Singh, Amar Subramanya, Fernando Pereira, and Andrew McCallum

    Technical Report (TR) UMASS-CS-2012-015, October, 2012, Jul 2013
14. Optimization and Learning in FACTORIE

    Alexandre Passos, Luke Vilnis, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Optimization for Machine Learning (NIPS WS), Jul 2013
15. Marginal Inference in MRFs using Frank-Wolfe

    David Belanger, Dan Sheldon, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Greedy Optimization, Frank-Wolfe and Friends (NIPS WS), Jul 2013
16. Anytime Belief Propagation Using Sparse Domains

    Sameer Singh, Sebastian Riedel, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Resource-Efficient Machine Learning (NIPS WS), Jul 2013

2012

1. Topic models for taxonomies

   Anton Bakalov, Andrew McCallum, Hanna M. Wallach, and David M. Mimno

   In Proceedings of the 12th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL), Washington, DC, USA, June 10-14, 2012, Jul 2012
2. An Integrated, Conditional Model of Information Extraction and Coreference with Applications to Citation Matching

   Ben Wellner, Andrew McCallum, Fuchun Peng, and Michael Hay

   arXiv preprint, Jul 2012
3. An Introduction to Conditional Random Fields

   Charles A. Sutton, and Andrew McCallum

   Foundations and Trends in Machine Learning, Jul 2012
4. MAP Inference in Chains using Column Generation

   David Belanger, Alexandre Passos, Sebastian Riedel, and Andrew McCallum

   In 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., Jul 2012
5. Combining joint models for biomedical event extraction

   David McClosky, Sebastian Riedel, Mihai Surdeanu, Andrew McCallum, and Christopher D. Manning

   BMC Bioinformatics, Jul 2012
6. Unsupervised Relation Discovery with Sense Disambiguation

   Limin Yao, Sebastian Riedel, and Andrew McCallum

   In 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, Jul 2012
7. A Discriminative Hierarchical Model for Fast Coreference at Large Scale

   Michael L. Wick, Sameer Singh, and Andrew McCallum

   In 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, Jul 2012
8. Selecting actions for resource-bounded information extraction using reinforcement learning

   Pallika H. Kanani, and Andrew McCallum

   In Proceedings of the Fifth International Conference on Web Search and Web Data Mining (WSDM), Seattle, WA, USA, February 8-12, 2012, Jul 2012
9. Monte Carlo MCMC: Efficient Inference by Approximate Sampling

   Sameer Singh, Michael L. Wick, and Andrew McCallum

   In 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, Jul 2012
10. Parse, Price and Cut–Delayed Column and Row Generation for Graph Based Parsers

    Sebastian Riedel, David A. Smith, and Andrew McCallum

    In 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, Jul 2012
11. Speeding up MAP with Column Generation and Block Regularization

    David Belanger, Alexandre Passos, Sebastian Riedel, and Andrew McCallum

    In ICML Workshop on Inferning: Interactions between Inference and Learning (ICML WS), Jul 2012
12. Human Machine Cooperation with Epistemological DBs: Supporting User Corrections to Automatically Constructed KBs

    Michael Wick, Karl Schultz, and  Andrew McCallum

    In NAACL Workshop on Automatic Knowledge Base Construction (AKBC), Jul 2012
13. Monte Carlo MCMC: Efficient Inference by Sampling Factors

    Sameer Singh, Michael Wick, and  Andrew McCallum

    In NAACL Workshop on Automatic Knowledge Base Construction (AKBC), Jul 2012

2011

1. Optimizing Semantic Coherence in Topic Models

   David M. Mimno, Hanna M. Wallach, Edmund M. Talley, Miriam Leenders, and Andrew McCallum

   In 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, Jul 2011
2. Toward interactive training and evaluation

   Gregory Druck, and Andrew McCallum

   In Proceedings of the 20th ACM Conference on Information and Knowledge Management (CIKM), Glasgow, United Kingdom, October 24-28, 2011, Jul 2011
3. Structured Relation Discovery using Generative Models

   Limin Yao, Aria Haghighi, Sebastian Riedel, and Andrew McCallum

   In 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, Jul 2011
4. Query-Aware MCMC

   Michael L. Wick, and Andrew McCallum

   In 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., Jul 2011
5. SampleRank: Training Factor Graphs with Atomic Gradients

   Michael L. Wick, Khashayar Rohanimanesh, Kedar Bellare, Aron Culotta, and Andrew McCallum

   In Proceedings of the 28th International Conference on Machine Learning (ICML), Bellevue, Washington, USA, June 28 - July 2, 2011, Jul 2011
6. Large-Scale Cross-Document Coreference Using Distributed Inference and Hierarchical Models

   Sameer Singh, Amarnag Subramanya, Fernando C. N. Pereira, and Andrew McCallum

   In 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, Jul 2011
7. Fast and Robust Joint Models for Biomedical Event Extraction

   Sebastian Riedel, and Andrew McCallum

   In 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, Jul 2011
8. Robust Biomedical Event Extraction with Dual Decomposition and Minimal Domain Adaptation

   Sebastian Riedel, and Andrew McCallum

   In Proceedings of BioNLP Shared Task 2011 Workshop, Portland, Oregon, USA, June 24, 2011, Jul 2011
9. Model Combination for Event Extraction in BioNLP 2011

   Sebastian Riedel, David McClosky, Mihai Surdeanu, Andrew McCallum, and Christopher D. Manning

   In Proceedings of BioNLP Shared Task 2011 Workshop, Portland, Oregon, USA, June 24, 2011, Jul 2011
10. Correlations and anticorrelations in LDA inference

    Alexandre Passos, Hanna Wallach, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Challenges in Learning Hierarchical Models: Transfer Learning and Optimization (NIPS WS), Jul 2011
11. Inducing Value Sparsity for Parallel Inference in Tree-shaped Models

    Sameer Singh, Brian Martin, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Computational Trade-offs in Statistical Learning (NIPS WS), Jul 2011
12. Towards Asynchronous Distributed MCMC Inference for Large Graphical Models

    Sameer Singh, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Algorithms, Systems, and Tools for Learning at Scale (NIPS WS), Jul 2011
13. Inter-Event Dependencies support Event Extraction from Biomedical Literature

    Roman Klinger, Sebastian Riedel, and Andrew McCallum

    In Mining Complex Entities from Network and Biomedical Data (MIND), Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), Jul 2011
14. Database of NIH grants using machine-learned categories and graphical clustering

    Edmund M Talley, David Newman, David Mimno, Bruce W Herr II, Hanna M Wallach, Gully Burns, Miriam Leenders, and Andrew McCallum

    Nature Methods, 8, 443–444, 27 May 2011, Jul 2011

2010

1. Generalized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data

   Gideon S. Mann, and Andrew McCallum

   Journal of Machine Learning Research (JMLR), Jul 2010
2. High-Performance Semi-Supervised Learning using Discriminatively Constrained Generative Models

   Gregory Druck, and Andrew McCallum

   In Proceedings of the 27th International Conference on Machine Learning (ICML), June 21-24, 2010, Haifa, Israel, Jul 2010
3. Collective Cross-Document Relation Extraction Without Labelled Data

   Limin Yao, Sebastian Riedel, and Andrew McCallum

   In 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, Jul 2010
4. Scalable Probabilistic Databases with Factor Graphs and MCMC

   Michael L. Wick, Andrew McCallum, and Gerome Miklau

   PVLDB, Jul 2010
5. Resource-Bounded Information Extraction: Acquiring Missing Feature Values on Demand

   Pallika H. Kanani, Andrew McCallum, and Shaohan Hu

   In Advances in Knowledge Discovery and Data Mining, 14th Pacific-Asia Conference (PAKDD), Hyderabad, India, June 21-24, 2010. Proceedings. Part I, Jul 2010
6. Constraint-Driven Rank-Based Learning for Information Extraction

   Sameer Singh, Limin Yao, Sebastian Riedel, and Andrew McCallum

   In 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, Jul 2010
7. Distantly Labeling Data for Large Scale Cross-Document Coreference

   Sameer Singh, Michael L. Wick, and Andrew McCallum

   arXiv preprint, Jul 2010
8. Inference by Minimizing Size, Divergence, or their Sum

   Sebastian Riedel, David A. Smith, and Andrew McCallum

   In UAI 2010, Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI), Catalina Island, CA, USA, July 8-11, 2010, Jul 2010
9. Modeling Relations and Their Mentions without Labeled Text

   Sebastian Riedel, Limin Yao, and Andrew McCallum

   In Machine Learning and Knowledge Discovery in Databases, European Conference (ECML PKDD), Barcelona, Spain, September 20-24, 2010, Proceedings, Part III, Jul 2010
10. An Introduction to Conditional Random Fields

    Charles Sutton, and Andrew McCallum

    In Foundations and Trends in Machine Learning (FnT ML), Jul 2010
11. Distantly labeling data for large scale cross-document coreference

    Sameer Singh, Michael Wick, and Andrew McCallum

    arXiv preprint, Jul 2010
12. Distributed MAP Inference for Undirected Graphical Models

    Sameer Singh, Amarnag Subramanya, Fernando Pereira, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Learning on Cores, Clusters, and Clouds (NIPS WS), Jul 2010
13. Machine Translation Using Overlapping Alignments and SampleRank

    Benjamin Roth, Andrew McCallum, Marc Dymetman, and Nicola Cancedda

    In Proceedings of the Ninth Conference of the Association for Machine Translation in the Americas (AMTA), Jul 2010

2009

1. Joint Inference for Natural Language Processing

   Andrew McCallum

   In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL), Boulder, Colorado, USA, June 4-5, 2009, Jul 2009
2. FACTORIE: Probabilistic Programming via Imperatively Defined Factor Graphs

   Andrew McCallum, Karl Schultz, and Sameer Singh

   In 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., Jul 2009
3. Piecewise training for structured prediction

   Charles A. Sutton, and Andrew McCallum

   Machine Learning (ML), Jul 2009
4. Polylingual Topic Models

   David M. Mimno, Hanna M. Wallach, Jason Naradowsky, David A. Smith, and Andrew McCallum

   In 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, Jul 2009
5. Active Learning by Labeling Features

   Gregory Druck, Burr Settles, and Andrew McCallum

   In 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, Jul 2009
6. Semi-supervised Learning of Dependency Parsers using Generalized Expectation Criteria

   Gregory Druck, Gideon S. Mann, and Andrew McCallum

   In 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, Jul 2009
7. Rethinking LDA: Why Priors Matter

   Hanna M. Wallach, David M. Mimno, and Andrew McCallum

   In 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., Jul 2009
8. Generalized Expectation Criteria for Bootstrapping Extractors using Record-Text Alignment

   Kedar Bellare, and Andrew McCallum

   In 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, Jul 2009
9. Alternating Projections for Learning with Expectation Constraints

   Kedar Bellare, Gregory Druck, and Andrew McCallum

   In UAI 2009, Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI), Montreal, QC, Canada, June 18-21, 2009, Jul 2009
10. Efficient methods for topic model inference on streaming document collections

    Limin Yao, David M. Mimno, and Andrew McCallum

    In Proceedings of the 15th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Paris, France, June 28 - July 1, 2009, Jul 2009
11. An Entity Based Model for Coreference Resolution

    Michael L. Wick, Aron Culotta, Khashayar Rohanimanesh, and Andrew McCallum

    In Proceedings of the SIAM International Conference on Data Mining (SDM), April 30 - May 2, 2009, Sparks, Nevada, USA, Jul 2009
12. Training Factor Graphs with Reinforcement Learning for Efficient MAP Inference

    Michael L. Wick, Khashayar Rohanimanesh, Sameer Singh, and Andrew McCallum

    In 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., Jul 2009
13. Bi-directional Joint Inference for Entity Resolution and Segmentation Using Imperatively-Defined Factor Graphs

    Sameer Singh, Karl Schultz, and Andrew McCallum

    In Machine Learning and Knowledge Discovery in Databases, European Conference (ECML PKDD), Bled, Slovenia, September 7-11, 2009, Proceedings, Part II, Jul 2009
14. SampleRank: Learning Preferences from Atomic Gradients

    Michael Wick, Khashayar Rohanimanesh, Aron Culotta, and Andrew McCallum

    In Neural Information Processing Systems Workshop on Advances in Ranking (NIPS WS), Jul 2009
15. Inference and Learning in Large Factor Graphs with Adaptive Proposal Distributions

    Khashayar Rohanimanesh, Michael Wick, and Andrew McCallum

    University of Massachusetts Technical Report #UM-CS-2009-008 (TR), Jul 2009
16. Advances in Learning and Inference for Partition-wise Models of Coreference Resolution

    Michael Wick, and Andrew McCallum

    University of Massachusets Technical Report # UM-CS-2009-028 (TR), Jul 2009
17. Representing Uncertainty in Databases with Scalable Factor Graphs

    Michael Wick

    Masters Thesis/Synthesis. Readers: Andrew McCallum and Gerome Miklau, Jul 2009
18. Towards Theoretical Bounds for Resource-bounded Information Gathering for Correlation Clustering

    Pallika Kanani, Andrew McCallum, and Ramesh Sitaraman

    UMass TechReport UM-CS-2009-027 (TR), Jul 2009
19. MAP inference in Large Factor Graphs with Reinforcement Learning

    Khashayar Rohanimanesh, Michael Wick, Sameer Singh, and  Andrew McCallum

    UMass Technical Report #UM-CS-2008-040 (TR), Jul 2009

2008

1. Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression

   David M. Mimno, and Andrew McCallum

   In UAI 2008, Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence (UAI), Helsinki, Finland, July 9-12, 2008, Jul 2008
2. Generalized Expectation Criteria for Semi-Supervised Learning of Conditional Random Fields

   Gideon S. Mann, and Andrew McCallum

   In ACL 2008, Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL), June 15-20, 2008, Columbus, Ohio, USA, Jul 2008
3. Learning from labeled features using generalized expectation criteria

   Gregory Druck, Gideon S. Mann, and Andrew McCallum

   In Proceedings of the 31st Annual International ACM Conference on Research and Development in Information Retrieval (SIGIR), Singapore, July 20-24, 2008, Jul 2008
4. A Discriminative Approach to Ontology Mapping

   Michael L. Wick, Khashayar Rohanimanesh, Andrew McCallum, and AnHai Doan

   In Proceedings of the International Workshop on New Trends in Information Integration (NTII), Auckland, New Zealand, August 23, 2008, Jul 2008
5. A unified approach for schema matching, coreference and canonicalization

   Michael L. Wick, Khashayar Rohanimanesh, Karl Schultz, and Andrew McCallum

   In Proceedings of the 14th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Las Vegas, Nevada, USA, August 24-27, 2008, Jul 2008
6. InterNano: e-Science for the Nanomanufacturing Community

   Rebecca Reznik-Zellen, Bob Stevens, Michael Thorn, Jeff Morse, Mark D. Smucker, James Allan, David M. Mimno, Andrew McCallum, and Mark Tuominen

   In Fourth International Conference on e-Science (e-Science), 7-12 December 2008, Indianapolis, IN, USA, Jul 2008
7. Unsupervised deduplication using cross-field dependencies

   Robert Hall, Charles A. Sutton, and Andrew McCallum

   In Proceedings of the 14th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Las Vegas, Nevada, USA, August 24-27, 2008, Jul 2008
8. Gibbs Sampling for Logistic Normal Topic Models with Graph-Based Priors

   David Mimno, Hanna Wallach, and Andrew McCallum

   In NIPS Workshop on Analyzing Graphs (NIPS WS), 2008, Whistler, BC., Jul 2008
9. FACTORIE: Efficient Probabilistic Programming for Relational Factor Graphs via Imperative Declarations of Structure, Inference and Learning

   Andrew McCallum, Khashayar Rohanemanesh, Michael Wick, Karl Schultz, and Sameer Singh

   In NIPS Workshop on Probabilistic Programming (NIPS WS), Jul 2008
10. A Discriminative Approach to Ontology Mapping

    Michael L. Wick, Khashayar Rohanimanesh, Andrew McCallum, and AnHai Doan

    In Proceedings of the International Workshop on New Trends in Information Integration (NTII 2008), Auckland, New Zealand, August 23, 2008, Jul 2008
11. Bayesian Modeling of Dependency Trees Using Hierarchical Pitman-Yor Priors

    Hanna Wallach, Charles Sutton, and Andrew McCallum

    In International Conference on Machine Learning, Workshop on Prior Knowledge for Text and Language Processing (ICML WS), Jul 2008
12. Learning to Predict the Quality of Contributions to Wikipedia

    Gregory Druck, Gerome Miklau, and Andrew McCallum

    In AAAI Workshop on Wikipedia and AI (AAAI WS), Jul 2008
13. Piecewise Training for Structured Prediction

    Charles Sutton, and Andrew McCallum

    Machine Learning Journal (MLJ), Jul 2008
14. Pachinko Allocation: Scalable Mixture Models of Topic Correlations

    Wei Li, and Andrew McCallum

    Submitted to the Journal of Machine Learning Research (JMLR), Jul 2008

2007

1. Topic and Role Discovery in Social Networks with Experiments on Enron and Academic Email

   Andrew McCallum, Xuerui Wang, and Andrés Corrada-Emmanuel

   J. Artif. Intell. Res., Jul 2007
2. First-Order Probabilistic Models for Coreference Resolution

   Aron Culotta, Michael L. Wick, and Andrew McCallum

   In 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, Jul 2007
3. Canonicalization of database records using adaptive similarity measures

   Aron Culotta, Michael L. Wick, Robert Hall, Matthew Marzilli, and Andrew McCallum

   In Proceedings of the 13th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Jose, California, USA, August 12-15, 2007, Jul 2007
4. Improved Dynamic Schedules for Belief Propagation

   Charles A. Sutton, and Andrew McCallum

   In UAI 2007, Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), Vancouver, BC, Canada, July 19-22, 2007, Jul 2007
5. Piecewise pseudolikelihood for efficient training of conditional random fields

   Charles A. Sutton, and Andrew McCallum

   In Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML), Corvallis, Oregon, USA, June 20-24, 2007, Jul 2007
6. Dynamic Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data

   Charles A. Sutton, Andrew McCallum, and Khashayar Rohanimanesh

   Journal of Machine Learning Research (JMLR), Jul 2007
7. Expertise modeling for matching papers with reviewers

   David M. Mimno, and Andrew McCallum

   In Proceedings of the 13th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Jose, California, USA, August 12-15, 2007, Jul 2007
8. Mining a digital library for influential authors

   David M. Mimno, and Andrew McCallum

   In ACM/IEEE Joint Conference on Digital Libraries (JCDL), Vancouver, BC, Canada, June 18-23, 2007, Proceedings, Jul 2007
9. Organizing the OCA: learning faceted subjects from a library of digital books

   David M. Mimno, and Andrew McCallum

   In ACM/IEEE Joint Conference on Digital Libraries (JCDL), Vancouver, BC, Canada, June 18-23, 2007, Proceedings, Jul 2007
10. Mixtures of hierarchical topics with Pachinko allocation

    David M. Mimno, Wei Li, and Andrew McCallum

    In Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML), Corvallis, Oregon, USA, June 20-24, 2007, Jul 2007
11. Cryptogram Decoding for OCR Using Numerization Strings

    Gary B. Huang, Erik G. Learned-Miller, and Andrew McCallum

    In 9th International Conference on Document Analysis and Recognition (ICDAR), 23-26 September, Curitiba, Paraná, Brazil, Jul 2007
12. Efficient Computation of Entropy Gradient for Semi-Supervised Conditional Random Fields

    Gideon S. Mann, and Andrew McCallum

    In 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, Jul 2007
13. Simple, robust, scalable semi-supervised learning via expectation regularization

    Gideon S. Mann, and Andrew McCallum

    In Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML), Corvallis, Oregon, USA, June 20-24, 2007, Jul 2007
14. Semi-supervised classification with hybrid generative/discriminative methods

    Gregory Druck, Chris Pal, Andrew McCallum, and Xiaojin Zhu

    In Proceedings of the 13th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Jose, California, USA, August 12-15, 2007, Jul 2007
15. WebKDD/SNAKDD 2007: web mining and social network analysis post-workshop report

    Haizheng Zhang, John Yen, C. Lee Giles, Bamshad Mobasher, Myra Spiliopoulou, Jaideep Srivastava, Olfa Nasraoui, and Andrew McCallum

    SIGKDD Explorations, Jul 2007
16. Resource-Bounded Information Gathering for Correlation Clustering

    Pallika H. Kanani, and Andrew McCallum

    In Learning Theory, 20th Annual Conference on Learning Theory (COLT), San Diego, CA, USA, June 13-15, 2007, Proceedings, Jul 2007
17. Improving Author Coreference by Resource-Bounded Information Gathering from the Web

    Pallika H. Kanani, Andrew McCallum, and Chris Pal

    In IJCAI 2007, Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, January 6-12, 2007, Jul 2007
18. People-LDA: Anchoring Topics to People using Face Recognition

    Vidit Jain, Erik G. Learned-Miller, and Andrew McCallum

    In IEEE 11th International Conference on Computer Vision (ICCV), Rio de Janeiro, Brazil, October 14-20, 2007, Jul 2007
19. Nonparametric Bayes Pachinko Allocation

    Wei Li, David M. Blei, and Andrew McCallum

    In UAI 2007, Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI), Vancouver, BC, Canada, July 19-22, 2007, Jul 2007
20. Topical N-Grams: Phrase and Topic Discovery, with an Application to Information Retrieval

    Xuerui Wang, Andrew McCallum, and Xing Wei

    In Proceedings of the 7th IEEE International Conference on Data Mining (ICDM), October 28-31, 2007, Omaha, Nebraska, USA, Jul 2007
21. Generalized component analysis for text with heterogeneous attributes

    Xuerui Wang, Chris Pal, and Andrew McCallum

    In Proceedings of the 13th ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), San Jose, California, USA, August 12-15, 2007, Jul 2007
22. Unsupervised Coreference of Publication Venues

    Robert Hall, Charles Sutton, and Andrew McCallum

    University of Massachusetts Amherst Technical Report (TR), Jul 2007
23. Generalized Expectation Criteria

    Andrew McCallum, Gideon Mann, and Gregory Druck

    University of Massachusetts Amherst Technical Report #2007-60 (TR), Jul 2007
24. Reducing Annotation Effort using Generalized Expectation Criteria–DRAFT

    Gregory Druck, Gideon Mann, and Andrew McCallum

    University of Massachusetts Amherst Technical Report #2007-62 (TR), Jul 2007
25. Community-based Link Prediction with Text

    David Mimno, Hanna M. Wallach, and Andrew McCallum

    In NIPS Workshop on Statistical Network Modeling (NIPS WS), Jul 2007
26. Leveraging Existing Resources using Generalized Expectation Criteria

    Gregory Druck, Gideon Mann, and Andrew McCallum

    In NIPS Workshop on Learning Problem Design (NIPS WS), Jul 2007
27. Lightly-Supervised Attribute Extraction for Web Search

    Kedar Bellare, Partha Pratim Talukdar, Giridhar Kumaran, Fernando Pereira, Mark Liberman, Andrew McCallum, and Mark Dredze

    In NIPS Workshop on Machine Learning for Web Search (NIPS WS), Jul 2007
28. Joint Group and Topic Discovery from Relations and Text

    Andrew McCallum, Xuerui Wang, and Natasha Mohanty

    Statistical Network Analysis: Models, Issues and New Directions, Lecture Notes in Computer Science 4503, pp. 28-44 (Book chapter), 2007, Jul 2007
29. Learning Extractors from Unlabeled Text using Relevant Databases

    Kedar Bellare, and Andrew McCallum

    In Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007, Jul 2007
30. Efficient Strategies for Improving Partitioning-Based Author Coreference by Incorporating Web Pages as Graph Nodes

    Pallika Kanani, and Andrew McCallum

    In Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007, Jul 2007
31. Probabilistic Representations for Integrating Unreliable Data Sources

    David Mimno, and Andrew McCallum

    In Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007, Jul 2007
32. Author Disambiguation using Error-Driven Machine Learning With a Ranking Loss Function

    Aron Culotta, Pallika Kanani, Robert Hall, Michael Wick, and  Andrew McCallum

    In Sixth International Workshop on Information Integration on the Web (IIWeb), collocated with AAAI, 2007, Jul 2007
33. Transfer Learning for Enhancing Information Flow in Organizations and Social Networks

    Chris Pal, Xuerui Wang, and Andrew McCallum

    In Submitted to Conference on Email and Spam (CEAS), 2007. Technical Note, Jul 2007
34. Sparse Message Passing Algorithms for Weighted Maximum Satisfiability

    Aron Culotta, Andrew McCallum, Bart Selman, and Ashish Sabharwal

    In New England Student Symposium on Artificial Intelligence (NESCAI), Jul 2007
35. Penn/UMass/CHOP BiocreativeII Systems

    Kuzman Ganchev, Koby Crammer, Fernando Pereira, Gideon Mann, Kedar Bellare, Andrew McCallum, Steven Carroll, Yang Jin, and  Peter White

    In BiocreativeII Evaluation Workshop, Jul 2007

2006

1. Information extraction, data mining and joint inference

   Andrew McCallum

   In Proceedings of the Twelfth ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Philadelphia, PA, USA, August 20-23, 2006, Jul 2006
2. Multi-Conditional Learning: Generative/Discriminative Training for Clustering and Classification

   Andrew McCallum, Chris Pal, Gregory Druck, and Xuerui Wang

   In 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, Jul 2006
3. Joint Group and Topic Discovery from Relations and Text

   Andrew McCallum, Xuerui Wang, and Natasha Mohanty

   In 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, Jul 2006
4. Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text

   Aron Culotta, Andrew McCallum, and Jonathan Betz

   In 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, Jul 2006
5. Corrective feedback and persistent learning for information extraction

   Aron Culotta, Trausti T. Kristjansson, Andrew McCallum, and Paul A. Viola

   Artif. Intell., Jul 2006
6. Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning

   B. Michael Kelm, Chris Pal, and Andrew McCallum

   In 18th International Conference on Pattern Recognition (ICPR), 20-24 August 2006, Hong Kong, China, Jul 2006
7. Reducing Weight Undertraining in Structured Discriminative Learning

   Charles A. Sutton, Michael Sindelar, and Andrew McCallum

   In 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, Jul 2006
8. Sparse Forward-Backward Using Minimum Divergence Beams for Fast Training Of Conditional Random Fields

   Chris Pal, Charles A. Sutton, and Andrew McCallum

   In 2006 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Toulouse, France, May 14-19, 2006, Jul 2006
9. Information extraction from research papers using conditional random fields

   Fuchun Peng, and Andrew McCallum

   Inf. Process. Manage., Jul 2006
10. Bibliometric impact measures leveraging topic analysis

    Gideon S. Mann, David M. Mimno, and Andrew McCallum

    In ACM/IEEE Joint Conference on Digital Libraries (JCDL), Chapel Hill, NC, USA, June 11-15, 2006, Proceedings, Jul 2006
11. Learning Field Compatibilities to Extract Database Records from Unstructured Text

    Michael L. Wick, Aron Culotta, and Andrew McCallum

    In EMNLP 2007, Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP), 22-23 July 2006, Sydney, Australia, Jul 2006
12. Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition

    Shaolei Feng, R. Manmatha, and Andrew McCallum

    In Second International Workshop on Document Image Analysis for Libraries (DIAL), 27-28 April 2006, Lyon, France, Jul 2006
13. Pachinko allocation: DAG-structured mixture models of topic correlations

    Wei Li, and Andrew McCallum

    In Machine Learning, Proceedings of the Twenty-Third International Conference (ICML), Pittsburgh, Pennsylvania, USA, June 25-29, 2006, Jul 2006
14. Table extraction for answer retrieval

    Xing Wei, W. Bruce Croft, and Andrew McCallum

    Inf. Retr., Jul 2006
15. Topics over time: a non-Markov continuous-time model of topical trends

    Xuerui Wang, and Andrew McCallum

    In Proceedings of the Twelfth ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD), Philadelphia, PA, USA, August 20-23, 2006, Jul 2006
16. On Discriminative and Semi-Supervised Dimensionality Reduction

    Chris Pal, Michael Kelm, Xuerui Wang, Greg Druck, and Andrew McCallum

    In Advances in Neural Information Processing Systems, Workshop on Novel Applications of Dimensionality Reduction (NIPS Workshop), Jul 2006
17. Tractable Learning and Inference with Higher-Order Representations

    Aron Culotta, and Andrew McCallum

    In ICML Workshop on Open Problems in Statistical Relational Learning (ICML WS), Jul 2006
18. CC Prediction with Graphical Models

    Chris Pal, and Andrew McCallum

    In Conference on Email and Anti-Spam (CEAS), Jul 2006
19. Practical Markov Logic Containing First-order Quantifiers with Application to Identity Uncertainty

    Aron Culotta, and Andrew McCallum

    In HLT Workshop on Computationally Hard Problems and Joint Inference in Speech and Language Processing, Jul 2006
20. A Continuous-Time Model of Topic Co-occurrence Trends

    Xuerui Wang, Wei Li, and  Andrew McCallum

    In AAAI Workshop on Event Detection (AAAI WS), Jul 2006
21. An Introduction to Conditional Random Fields for Relational Learning

    Charles Sutton, and Andrew McCallum

    Book chapter in Introduction to Statistical Relational Learning, Jul 2006
22. Semi-supervised Text Classification Using EM

    Kamal Nigam, Andrew McCallum, and Tom Mitchell

    Book chapter in Semi-Supervised Learning, Jul 2006

2005

1. Information extraction: distilling structured data from unstructured text

   Andrew McCallum

   ACM Queue, Jul 2005
2. Topic and Role Discovery in Social Networks

   Andrew McCallum, Andrés Corrada-Emmanuel, and Xuerui Wang

   In IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), Edinburgh, Scotland, UK, July 30 - August 5, 2005, Jul 2005
3. A Conditional Random Field for Discriminatively-trained Finite-state String Edit Distance

   Andrew McCallum, Kedar Bellare, and Fernando C. N. Pereira

   In UAI ’05, Proceedings of the 21st Conference in Uncertainty in Artificial Intelligence (UAI), Edinburgh, Scotland, July 26-29, 2005, Jul 2005
4. Joint deduplication of multiple record types in relational data

   Aron Culotta, and Andrew McCallum

   In Proceedings of the 2005 ACM International Conference on Information and Knowledge Management (CIKM), Bremen, Germany, October 31 - November 5, 2005, Jul 2005
5. Reducing Labeling Effort for Structured Prediction Tasks

   Aron Culotta, and Andrew McCallum

   In 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, Jul 2005
6. Composition of Conditional Random Fields for Transfer Learning

   Charles A. Sutton, and Andrew McCallum

   In 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, Jul 2005
7. Joint Parsing and Semantic Role Labeling

   Charles A. Sutton, and Andrew McCallum

   In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL), Ann Arbor, Michigan, USA, June 29-30, 2005, Jul 2005
8. Piecewise Training for Undirected Models

   Charles A. Sutton, and Andrew McCallum

   In UAI ’05, Proceedings of the 21st Conference in Uncertainty in Artificial Intelligence (UAI), Edinburgh, Scotland, July 26-29, 2005, Jul 2005
9. Collective multi-label classification

   Nadia Ghamrawi, and Andrew McCallum

   In Proceedings of the 2005 ACM International Conference on Information and Knowledge Management (CIKM), Bremen, Germany, October 31 - November 5, 2005, Jul 2005
10. Disambiguating Web appearances of people in a social network

    Ron Bekkerman, and Andrew McCallum

    In Proceedings of the 14th international conference on World Wide Web (WWW), Chiba, Japan, May 10-14, 2005, Jul 2005
11. Multi-way distributional clustering via pairwise interactions

    Ron Bekkerman, Ran El-Yaniv, and Andrew McCallum

    In Machine Learning, Proceedings of the Twenty-Second International Conference (ICML), Bonn, Germany, August 7-11, 2005, Jul 2005
12. Semi-Supervised Sequence Modeling with Syntactic Topic Models

    Wei Li, and Andrew McCallum

    In 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, Jul 2005
13. Group and topic discovery from relations and text

    Xuerui Wang, Natasha Mohanty, and Andrew McCallum

    In Proceedings of the 3rd international workshop on Link discovery (LinkKDD), Chicago, Illinois, USA, August 21-25, 2005, Jul 2005
14. Group and Topic Discovery from Relations and Their Attributes

    Xuerui Wang, Natasha Mohanty, and Andrew McCallum

    In Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems (NIPS), December 5-8, 2005, Vancouver, British Columbia, Canada], Jul 2005
15. Detecting Anomalies in Network Traffic Using Maximum Entropy Estimation

    Yu Gu, Andrew McCallum, and Donald F. Towsley

    In Proceedings of the 5th Internet Measurement Conference (IMC), Berkeley, California, USA, October 19-21, 2005, Jul 2005
16. A Note on Topical N-grams

    Xuerui Wang, and Andrew McCallum

    University of Massachusetts Technical Report UM-CS-2005-071 (TR), Jul 2005
17. Pachinko allocation: A Directed Acyclic Graph for Topic Correlations

    Wei Li, and Andrew McCallum

    In NIPS Workshop on Nonparametric Bayesian Methods (NIPS WS), Jul 2005
18. Direct Maximization of Rank-Based Metrics for Information Retrieval

    W. Bruce Croft Don Metzler, and Andrew McCallum

    CIIR Technical Report IR-429 (TR), Jul 2005
19. Learning Clusterwise Similarity with First-order Features

    Aron Culotta, and Andrew McCallum

    In NIPS Workshop on the Theoretical Foundations of Clustering (NIPS WS), Jul 2005
20. Feature Bagging: Preventing Weight Undertraining in Structured Discriminative Learning

    Charles Sutton, Michael Sindelar, and Andrew McCallum

    Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-402 (TR), Jul 2005
21. Fast, Piecewise Training for Discriminative Finite-state and Parsing Models

    Charles Sutton, and Andrew McCallum

    Center for Intelligent Information Retrieval Technical Report IR-403 (TR), Jul 2005
22. Practical Markov Logic Containing First-order Quantifiers with Application to Identity Uncertainty

    Aron Culotta, and Andrew McCallum

    Technical Report IR-430, University of Massachusetts (TR), Jul 2005
23. A Conditional Model of Deduplication for Multi-type Relational Data

    Aron Culotta, and Andrew McCallum

    Technical Report IR-443, University of Massachusetts (TR), Jul 2005
24. Predictive Random Fields: Latent Variable Models Fit by Multiway Conditional Probability with Applications to Document Analysis

    Andrew McCallum, Xuerui Wang, and Chris Pal

    UMass Technical Report UM-CS-2005-053, version 2.1 (TR), Jul 2005
25. Gene Prediction with Conditional Random Fields

    Aron Culotta, David Kulp, and Andrew McCallum

    Technical Report UM-CS-2005-028, University of Massachusetts, Amherst (TR), Jul 2005
26. Constrained Kronecker Deltas for Fast Approximate Inference and Estimation

    Chris Pal, Charles Sutton, and Andrew McCallum

    In Submitted to UAI, Jul 2005

2004

1. Conditional Models of Identity Uncertainty with Application to Noun Coreference

   Andrew McCallum, and Ben Wellner

   In Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems (NIPS), December 13-18, 2004, Vancouver, British Columbia, Canada], Jul 2004
2. Extracting social networks and contact information from email and the Web

   Aron Culotta, Ron Bekkerman, and Andrew McCallum

   In CEAS 2004 - First Conference on Email and Anti-Spam (CEAS), July 30-31, 2004, Mountain View, California, USA, Jul 2004
3. An Integrated, Conditional Model of Information Extraction and Coreference with Appli

   Ben Wellner, Andrew McCallum, Fuchun Peng, and Michael Hay

   In UAI ’04, Proceedings of the 20th Conference in Uncertainty in Artificial Intelligence (UAI), Banff, Canada, July 7-11, 2004, Jul 2004
4. Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data

   Charles A. Sutton, Khashayar Rohanimanesh, and Andrew McCallum

   In Machine Learning, Proceedings of the Twenty-first International Conference (ICML), Banff, Alberta, Canada, July 4-8, 2004, Jul 2004
5. Accurate Information Extraction from Research Papers using Conditional Random Fields

   Fuchun Peng, and Andrew McCallum

   In Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), Boston, Massachusetts, USA, May 2-7, 2004, Jul 2004
6. Chinese Segmentation and New Word Detection using Conditional Random Fields

   Fuchun Peng, Fangfang Feng, and Andrew McCallum

   In COLING 2004, 20th International Conference on Computational Linguistics, Proceedings of the Conference (COLING), 23-27 August 2004, Geneva, Switzerland, Jul 2004
7. Interactive Information Extraction with Constrained Conditional Random Fields

   Trausti T. Kristjansson, Aron Culotta, Paul A. Viola, and Andrew McCallum

   In 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, Jul 2004
8. Piecewise Training with Parameter Independence Diagrams: Comparing Globally- and Locally-trained Linear-chain CRFs

   Andrew McCallum, and Charles Sutton

   Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-383 (TR), Jul 2004
9. Automatic Categorization of Email into Folders: Benchmark Experiments on Enron and SRI Corpora

   Ron Bekkerman, Andrew McCallum, and Gary Huang

   Center for Intelligent Information Retrieval, University of Massachusetts Technical Report IR-383 (TR), Jul 2004
10. The Author-Recipient-Topic Model for Topic and Role Discovery in Social Networks: Experiments with Enron and Academic Email

    Andrew McCallum, Andres Corrada-Emmanuel, and Xuerui Wang

    Technical Report UM-CS-2004-096 (TR), Jul 2004
11. Collective Segmentation and Labeling of Distant Entities in Information Extraction

    Charles Sutton, and Andrew McCallum

    In ICML workshop on Statistical Relational Learning (ICML WS), Jul 2004
12. An Exploration of Entity Models, Collective Classification and Relation Description

    Hema Raghavan, James Allan, and Andrew McCallum

    In KDD Workshop on Link Analysis and Group Detection (KDD WS), Jul 2004
13. Sign Detection in Natural Images with Conditional Random Fields

    Jerod Weinman, Al Hansen, and Andrew McCallum

    In IEEE International Workshop on Machine Learning for Signal Processing, Jul 2004
14. Confidence Estimation for Information Extraction

    Aron Culotta, and Andrew McCallum

    In Proceedings of Human Language Technology Conference and North American Chapter of the Association for Computational Linguistics (HLT-NAACL), Jul 2004
15. A Note on Semi-supervised Learning using Markov Random Fields

    Wei Li, and Andrew McCallum

    Technical Note, February 3, 2004, Jul 2004

2003

1. Efficiently Inducing Features of Conditional Random Fields

   Andrew McCallum

   In UAI ’03, Proceedings of the 19th Conference in Uncertainty in Artificial Intelligence (UAI), Acapulco, Mexico, August 7-10 2003, Jul 2003
2. Toward Conditional Models of Identity Uncertainty with Application to Proper Noun Coreference

   Andrew McCallum, and Ben Wellner

   In Proceedings of IJCAI-03 Workshop on Information Integration on the Web (IIWeb-03), August 9-10, 2003, Acapulco, Mexico, Jul 2003
3. Early results for Named Entity Recognition with Conditional Random Fields, Feature Induction and Web-Enhanced Lexicons

   Andrew McCallum, and Wei Li

   In 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, Jul 2003
4. Table Extraction Using Conditional Random Fields

   David Pinto, Andrew McCallum, Xing Wei, and W. Bruce Croft

   In Proceedings of the 2003 Annual National Conference on Digital Government Research (DG.O), 2003, Jul 2003
5. Table extraction using conditional random fields

   David Pinto, Andrew McCallum, Xing Wei, and W. Bruce Croft

   In 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, Jul 2003
6. 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

   James Allan, Jay Aslam, Nicholas J. Belkin, Chris Buckley, James P. Callan, W. Bruce Croft, Susan T. Dumais, Norbert Fuhr, Donna Harman, David J. Harper, Djoerd Hiemstra, Thomas Hofmann, Eduard H. Hovy, Wessel Kraaij, John D. Lafferty, Victor Lavrenko, David D. Lewis, Liz Liddy, R. Manmatha, Andrew McCallum, Jay M. Ponte, John M. Prager, Dragomir R. Radev, Philip Resnik, Stephen E. Robertson, Ronald Rosenfeld, Salim Roukos, Mark Sanderson, Richard M. Schwartz, Amit Singhal, Alan F. Smeaton, Howard R. Turtle, Ellen M. Voorhees, Ralph M. Weischedel, Jinxi Xu, and ChengXiang Zhai

   SIGIR Forum, Jul 2003
7. Classification with Hybrid Generative/Discriminative Models

   Rajat Raina, Yirong Shen, Andrew Y. Ng, and Andrew McCallum

   In Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems (NIPS), December 8-13, 2003, Vancouver and Whistler, British Columbia, Canada], Jul 2003
8. Rapid development of Hindi named entity recognition using conditional random fields and feature induction

   Wei Li, and Andrew McCallum

   ACM Trans. Asian Lang. Inf. Process., Jul 2003
9. Dynamic Conditional Random Fields for Jointly Labeling Multiple Sequences

   Andrew McCallum, Khashayar Rohanimanesh, and Charles Sutton

   In NIPS*2003 Workshop on Syntax, Semantics, Statistics (NIPS WS), Jul 2003
10. A Note on the Unification of Information Extraction and Data Mining using Conditional-Probability, Relational Models

    Andrew McCallum, and David Jensen

    In IJCAI’03 Workshop on Learning Statistical Models from Relational Data (IJCAI WS), Jul 2003
11. Object Consolidation by Graph Partitioning with a Conditionally-trained Distance Metric

    Andrew McCallum, and Ben Wellner

    In KDD Workshop on Data Cleaning, Record Linkage and Object Consolidation (KDD WS), Jul 2003

2002

1. Learning with Scope, with Application to Information Extraction and Classification

   David M. Blei, J. Andrew Bagnell, and Andrew McCallum

   In UAI ’02, Proceedings of the 18th Conference in Uncertainty in Artificial Intelligence (UAI), University of Alberta, Edmonton, Alberta, Canada, August 1-4, 2002, Jul 2002

2001

1. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

   John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira

   In Proceedings of the Eighteenth International Conference on Machine Learning (ICML), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001, Jul 2001
2. Toward Optimal Active Learning through Sampling Estimation of Error Reduction

   Nicholas Roy, and Andrew McCallum

   In Proceedings of the Eighteenth International Conference on Machine Learning (ICML), Williams College, Williamstown, MA, USA, June 28 - July 1, 2001, Jul 2001
3. Unlocking the Information in Text

   Dallan Quass, Andrew McCallum, and William Cohen

   In The Future of Software, Winter 2000/2001, Jul 2001

2000

1. Maximum Entropy Markov Models for Information Extraction and Segmentation

   Andrew McCallum, Dayne Freitag, and Fernando C. N. Pereira

   In Proceedings of the Seventeenth International Conference on Machine Learning (ICML), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000, Jul 2000
2. Automating the Construction of Internet Portals with Machine Learning

   Andrew McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore

   Inf. Retr., Jul 2000
3. Efficient clustering of high-dimensional data sets with application to reference matching

   Andrew McCallum, Kamal Nigam, and Lyle H. Ungar

   In Proceedings of the sixth ACM international conference on Knowledge discovery and data mining (SIGKDD), Boston, MA, USA, August 20-23, 2000, Jul 2000
4. Information Extraction with HMM Structures Learned by Stochastic Optimization

   Dayne Freitag, and Andrew McCallum

   In 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., Jul 2000
5. Learning to Create Customized Authority Lists

   Huan Chang, David Cohn, and Andrew McCallum

   In Proceedings of the Seventeenth International Conference on Machine Learning (ICML), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000, Jul 2000
6. Text Classification from Labeled and Unlabeled Documents using EM

   Kamal Nigam, Andrew McCallum, Sebastian Thrun, and Tom M. Mitchell

   Machine Learning (ML), Jul 2000
7. Learning to construct knowledge bases from the World Wide Web

   Mark Craven, Dan DiPasquo, Dayne Freitag, Andrew McCallum, Tom M. Mitchell, Kamal Nigam, and Seán Slattery

   Artif. Intell., Jul 2000
8. Learning to Understand the Web

   William W. Cohen, Andrew McCallum, and Dallan Quass

   IEEE Data Eng. Bull., Jul 2000
9. Semi-supervised Clustering with User Feedback

   David Cohn, Rich Caruana, and Andrew McCallum

   In Submitted to AAAI 2000, Jul 2000

1999

1. A Machine Learning Approach to Building Domain-Specific Search Engines

   Andrew McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore

   In Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI) Stockholm, Sweden, July 31 - August 6, 1999. 2 Volumes, 1450 pages, Jul 1999
2. Using Reinforcement Learning to Spider the Web Efficiently

   Jason Rennie, and Andrew McCallum

   In Proceedings of the Sixteenth International Conference on Machine Learning (ICML), Bled, Slovenia, June 27 - 30, 1999, Jul 1999
3. Creating customized authority lists

   Huan Chang, David Cohn, and Andrew McCallum

   In Proceedings of the 17th International Conference on Machine Learning (ICML), Jul 1999
4. Multi-Label Text Classification with a Mixture Model Trained by EM

   Andrew McCallum

   In AAAI’99 Workshop on Text Learning (AAAI WS), Jul 1999
5. A Hierarchical Probabilistic Model for Novelty Detection in Text

   Doug Baker, Thomas Hofmann, Andrew McCallum, and Yiming Yang

   In Submitted to NIPS’99, Jul 1999
6. Using Maximum Entropy for Text Classification

   Kamal Nigam, John Lafferty, and Andrew McCallum

   In IJCAI’99 Workshop on Information Filtering (IJCAI WS), Jul 1999
7. Information Extraction with HMMs and Shrinkage

   Dayne Frietag, and Andrew McCallum

   In AAAI’99 Workshop on Machine Learning for Information Extraction (AAAI WS), Jul 1999
8. Learning Hidden Markov Model Structure for Information Extraction

   Kristie Seymore, Andrew McCallum, and Roni Rosenfeld

   In AAAI’99 Workshop on Machine Learning for Information Extraction (AAAI WS), Jul 1999
9. Bootstrapping for Text Learning Tasks

   Rosie Jones, Andrew McCallum, Kamal Nigam, and Ellen Riloff

   In IJCAI-99 Workshop on Text Mining: Foundations, Techniques and Applications (IJCAI WS), Jul 1999
10. Building Domain-Specific Search Engines with Machine Learning Techniques

    Andrew McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore

    In AAAI-99 Spring Symposium (AAAI-SS), Jul 1999

1998

1. Employing EM and Pool-Based Active Learning for Text Classification

   Andrew McCallum, and Kamal Nigam

   In Proceedings of the Fifteenth International Conference on Machine Learning (ICML), Madison, Wisconsin, USA, July 24-27, 1998, Jul 1998
2. Improving Text Classification by Shrinkage in a Hierarchy of Classes

   Andrew McCallum, Ronald Rosenfeld, Tom M. Mitchell, and Andrew Y. Ng

   In Proceedings of the Fifteenth International Conference on Machine Learning (ICML), Madison, Wisconsin, USA, July 24-27, 1998, Jul 1998
3. Learning to Classify Text from Labeled and Unlabeled Documents

   Kamal Nigam, Andrew McCallum, Sebastian Thrun, and Tom M. Mitchell

   In 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., Jul 1998
4. Distributional Clustering of Words for Text Classification

   L. Douglas Baker, and Andrew McCallum

   In SIGIR ’98: Proceedings of the 21st Annual International ACM Conference on Research and Development in Information Retrieval (SIGIR), August 24-28 1998, Melbourne, Australia, Jul 1998
5. Learning to Extract Symbolic Knowledge from the World Wide Web

   Mark Craven, Dan DiPasquo, Dayne Freitag, Andrew McCallum, Tom M. Mitchell, Kamal Nigam, and Seán Slattery

   In 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., Jul 1998
6. A Comparison of Event Models for Naive Bayes Text Classification

   Andrew McCallum, and Kamal Nigam

   In AAAI-98 Workshop on "Learning for Text Categorization" (AAAI WS), Jul 1998

1997

1. Efficient Exploration in Reinforcement Learning with Hidden State

   Andrew McCallum

   In AAAI Fall Symposium on "Model-directed Autonomous Systems", Jul 1997

1996

1. Hidden State and Reinforcement Learning with Instance-Based State Identification

   Andrew McCallum

   IEEE Transations on Systems, Man and Cybernetics, Special issue on Robot Learning, Jul 1996
2. Learning to Use Selective Attention and Short-Term Memory in Sequential Tasks

   Andrew McCallum

   In From Animals to Animats, Fourth International Conference on Simulation of Adaptive Behavior, (SAB’96). Cape Cod, Massachusetts., Jul 1996

1995

1. Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State

   Andrew McCallum

   In Machine Learning, Proceedings of the Twelfth International Conference on Machine Learning, Tahoe City, California, USA, July 9-12, 1995, Jul 1995
2. Reinforcement Learning with Selective Perception and Hidden State

   Andrew McCallum

   PhD. thesis, Jul 1995

1994

1. Instance-Based State Identification for Reinforcement Learning

   Andrew McCallum

   In Advances in Neural Information Processing Systems 7, (NIPS), Denver, Colorado, USA, Jul 1994
2. First Results with Instance-Based State Identification for Reinforcement Learning

   Andrew McCallum

   URCS Tech Report 502 (TR), Jul 1994
3. Reduced Training Time for Reinforcement Learning with Hidden State

   Andrew McCallum

   In The Proceedings of the Eleventh International Machine Learning Workshop, Robot Learning, New Brunswick, NJ, Jul 1994
4. Short-Term Memory in Visual Routines for ‘Off-Road Car Chasing’

   Andrew McCallum

   In Working Notes of AAAI Spring Symposium Series, "Toward Physical Interaction and Manipulation", Stanford University, March 21-23, Jul 1994

1993

1. Overcoming Incomplete Perception with Util Distinction Memory

   Andrew McCallum

   In Machine Learning, Proceedings of the Tenth International Conference, University of Massachusetts, Amherst, MA, USA, June 27-29, 1993, Jul 1993
2. Learning with Incomplete Selective Perception

   Andrew McCallum

   URCS Tech Report 453 (TR), Jul 1993
3. Linking Shared Segments

   William E Garrett, Michael L Scott, Ricardo Bianchini, Leonidas I Kontothanassis, Andrew McCallum, Jeffrey A Thomas, Robert W Wisniewski, and Steve Luk

   In Winter USENIX, San Diego, CA, Jul 1993

1992

1. Using Transitional Proximity for Faster Reinforcement Learning

   Andrew McCallum

   In Proceedings of the Ninth International Workshop on Machine Learning (ML WS), Aberdeen, Scotland, UK, July 1-3, 1992, Jul 1992
2. First Results with Utile Distinction Memory for Reinforcement Learning

   Andrew McCallum

   URCS Tech Report 446 (TR), Jul 1992
3. Dynamic Sharing and Backward Compatibility on 64-Bit Machines

   William E Garrett, LI Bianchini, LI Kontothanassis, Andrew McCallum, Jeffery Thomas, Robert Wisniewski, and Michael L Scott

   URCS Tech Report 418 (TR), Jul 1992

1991

1990

1. Using Genetic Algorithms to Learn Disjunctive Rules from Examples

   Andrew McCallum, and Kent A. Spackman

   In Machine Learning, Proceedings of the Seventh International Conference on Machine Learning (ICML), Austin, Texas, USA, June 21-23, 1990, Jul 1990