"Syntactic Language Modeling"   Visionary Talk

03/25/05: 10:30 AM, webcast
11th Floor Small and Large Conference Rooms
Host: Patrick Pantel, schedule

Abstract: A language model is probably distribution over all sentences in a language. Traditionally they are associated with speech recognition systems where they help the system distinguish between word sentences which sound the same but with very different probabilities of being uttered (e.g., "the big/pig dog"). In this talk I first argue for the utility of language modeling in many natural-language processing tasks. In particular I describe a language model based upon a probabilistic parser for English. and its use in two quite distinct NLP tasks: machine translation and detecting speech repairs. Most people have some idea of what machine translation is, but speech repairs are less discussed. Frequently in speech people hesitate and then rephare something they started to say. ("I need a uh want a ticket to Boston.") Often this is seen as a reason why grammatical models might not be useful in speech. Contrariwise, its ungrammticality should cause a syntactic model to assign such sequence very low probability compared to the same sequence without the mistake. This in turn might aid in correcting for them. We show this is the case. In the final portion of the talk I motivate my interest in language modeling by relating it to my long range vision of NLP in particular, and AI in general. This is a joint work with Mark Johnson, Kevin Knight and Kenji Yamada.

About Eugene Charniak: Eugene Charniak is a Professor of Computer Science and Cognitive Science at Brown University and is a past Chairman of the Department of Computer Science (1991-1997). He received his A.B. degree in Physics from University of Chicago, and a Ph.D. from M.I.T. in Computer Science. He has published four books, the most recent being Statistical Language Learning (1993). He is a Fellow of the American Association of Artificial Intelligence and was previously a Councilor of the organization. He is on the editorial boards of several journals and was a founding editor of the journal "Cognitive Science". His research has always been in the area of language understanding and technologies which relate to it. Over the last ten years he has been interested in statistical techniques for language understanding, and more specifically in the use of statistical methods in syntactic parsing, speech recognition, and machine translation.

Last updated: Mon Jun 19 17:44:06 2006