"Dynamic Bayesian Nets for Language Modeling"
 
             Dr. Leon  Peshkin,  Harvard University
 
 Dynamic Bayesian networks (DBNs) offer an elegant way to integrate various
 aspects of language in one model. Many existing algorithms developed for
 learning and inference in DBNs are applicable to probabilistic language
 modeling. To demonstrate the potential of DBNs for natural language
 processing, we employ a DBN for information extraction and part-of-speech
 tagging tasks. Our methods outperform previously published results on an
 established benchmark domain. 
 
 This talk will overview the following papers, avilable from
    http://www.ai.mit.edu/~pesha/Public/papers.html
 
"A Minimalist Approach to Part-Of-Speech Tagging" (in review)  8 pages
 - How simple a PoS tagger could we make  ?
 - How could it be trained independently, then integrated into a system?
 - Is the key to PoS tagging in the features or in the model after all ?
 - Do linguistic fetures really help ?
 
"Bayesian Nets in Syntactic Categorization of Novel Words" (submitted) 3 pages
 - Our PoS tagger fares well on novel data, trained on WSJ, 
   tested on Brown corpus, email corpus and even "Jabberwocky".
 
"Bayesian Information Extraction Network"  accepted  IJCAI - 2003  8 pages
 - We assemble wealth of emerging linguistic instruments for shallow parsing,
   syntactic and semantic tagging, morphological decomposition, named entity
   recognition etc. in order to incrementally build a robust information
   extraction system.
 
"Integrated probabilistic reasoning about text" (in preparation) 8 pages
 - This paper presents an alternative architecture for probabilistic 
   inference about text which performs integrated reasoning about
   syntactic and semantic categories.
 - Demonstrates the power of approximate inference algorithms for NLP.