Eduard Hovy - Toward a New Computational Theory of Semantics - Part 1/2
Bio:Eduard Hovy directs the Natural Language Research Group at USC's Information Sciences Institute and serves as Deputy Director of the Intelligent Systems Division and as research associate professor of the Computer Science Department. He also directs the DHS Centre for Knowledge Integration and Discovery at the University of Southern California and is Director of Research of its Digital Government Research Centre. He completed a Ph.D. in Computer Science (Artificial Intelligence) at Yale University in 1987. His research focuses on information extraction, automated text summarization, the semi-automated construction of large lexicons and ontologies, machine translation, question answering, and digital government. Abstract:In his talk Eduard Hovy argues for a new kind of semantics, growing from recent work in NLP ii Distributional Semantics, that combines traditional symbolic logic-based semantics with (computation-based) statistical word distribution information. The core resource is a single lexico-semantic lexicon that can be used for a variety of tasks, provided that it is reformulated accordingly. I show how to define such a semantics, how to build the appropriate lexicon, how to format it, and how to use it for various tasks. The talk pulls together a wide range of related topics, including Pantel-style resources like DIRT, inferences / expectations such as those used in Schank-style expectation-based parsing and expectation-driven NLU, PropBank-style word valence lexical items, and the treatment of negation and modalities.