Computer Science Colloquium
“Statistical Relational Learning for Textual Inference”
Dr. Ray Mooney
Professor of Computer Science
University of Texas at Austin
Statistical Relational Learning (SRL) studies the integration of first-order logic and probabilistic graphical models for learning and inference in complex relational domains. As such, SRL is particularly suited for making uncertain structured inferences from natural-language text, and allowing a system to "read between the lines" and infer implicit information that is not explicitly stated. This talk will review our recent work on using two SRL methods for textual inference. First, I will discuss learning Bayesian Logic Programs (BLPs) from facts automatically extracted from a document corpus, and then using the resulting BLPs to infer implicit relations when reading future documents. Second, we discuss representing the the semantic interpretation of a sentence as a Markov Logic Network (MLN) by integrating the logical form generated by a parser with distributional lexical semantics. This approach allows a rich semantic representation of natural language that incorporates both logical structure and probabilistic information about word sense. The resulting MLNs support making complex textual inferences of both similarity and entailment.
Raymond J. Mooney is a Professor in the Department of Computer Science at the University of Texas at Austin. He received his Ph.D. in 1988 from the University of Illinois at Urbana/Champaign. He is an author of over 150 published research papers, primarily in the areas of machine learning and natural language processing. He was the President of the International Machine Learning Society from 2008-2011, and program co-chair for the 2006 AAAI Conference on Artificial Intelligence, general chair of the 2005 Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, and co-chair of the 1990 International Conference on Machine Learning. He is a Fellow of both the American Association for Artificial Intelligence and the Association for Computing Machinery, and the recipient of best paper awards from the National Confere nce on Artificial Intelligence, the SIGKDD International Conference on Knowledge Discovery and Data Mining, the International Conference on Machine Learning, and the Annual Meeting of the Association for Computational Linguistics. His recent research has focused on learning for natural-language processing, connecting language and perception, statistical relational learning, and transfer learning.