June 30th, 2012, Edinburgh, UK
The workshop is organized by IESL members Sameer Singh, Michael Wick and Andrew McCallum.
This workshop studies the interactions between algorithms that learn a model, and algorithms that use the resulting model parameters for inference. These interactions are studied from two perspectives.
The first perspective studies how the choice of an inference algorithm influences the parameters the model ultimately learns. For example, many parameter estimation algorithms require inference as a subroutine. Consequently, when we are faced with models for which exact inference is expensive, we must use an approximation instead: MCMC sampling, belief propagation, beam-search, etc. On some problems these approximations yield superior models, yet on others, they fail catastrophically. We invite studies that analyze (both empirically and theoretically) the impact of approximate inference on the resulting model. How does approximate inference alter the learning objective? Affect generalization? Influence convergence properties? Further, does the behavior of inference change as learning continues to improve the quality of the model?
A second perspective from which we study these interactions is by considering how the learning objective and model parameters can impact both the quality and performance of inference during “test time.” These unconventional approaches to learning combine generalization to unseen data with other desiderata such as fast inference. For example, work in structured cascades learns model for which greedy, efficient inference can be performed at test time while still maintaining accuracy guarantees. Similarly, there has been work that learns operators for efficient search-based inference. There has also been work that incorporates resource constraints on running time and memory into the learning objective.
NAACL-HLT 2012 Joint Workshop on June 7-8, 2012, Montreal, Canada
Automatic Knowledge Base Construction and Web-scale Knowledge Extraction
The workshop is organized by IESL member Sebastian Riedel.
Recently, there has been a significant amount of interest in automatically creating large-scale knowledge bases (KBs) from unstructured text. The Web-scale knowledge extraction task presents a unique set of opportunities and challenges. The resulting knowledge bases can have the advantage of scale and coverage. They have been enriched by linking to the Semantic Web, in particular the growing linked open dataset (LOD). These semantic knowledge bases have been used for a wide variety of Natural Language Processing, Knowledge Representation, and Reasoning applications such as semantic search, question answering, entity resolution, ontology mapping etc. The automatic construction of these KBs has been enabled by research in areas including natural language processing, information extraction, information integration, databases, search and machine learning. There are substantial scientific and engineering challenges in advancing and integrating such relevant methodologies.
With this year’s workshop, we would like to resume the positive experiences from two previous workshops: AKBC-2010 and WEKEX-2011. The joint AKBC-WEKEX workshop will serve as a forum for researchers working in the area of automated knowledge harvesting from text. By having invited talks by leading researchers from industry, academia, and the government, and by focusing particularly on vision papers, we aim to provide a vivid forum of discussion about the field of automated knowledge base construction.