Endorsed by SIGNLL, the Association for Computational Linguistics (ACL) Special Interest Group (SIG) on Natural Language Learning.

For a description of the workshop, see the Call for Papers

Program

9:00-9:15 Welcome

9:15-10:15 INVITED TALK, Lillian Lee, Cornell University

   "Unsupervised Segmentation of Japanese"

10:15-10:40 Coffee Break 

10:40-12:10  Paper Session I

   "Dual Distributional Verb Sense Disambiguation with Small Corpora and Machine Readable Dictionaries"
   Jeong-Mi Cho, Jungyun Seo, and Gil Chang Kim, Sogang University and Korea Advanced Institute of Science and Technology

   "A Computational Approach to Deciphering Unknown Scripts"
   Kevin Knight and Kenji Yamada, USC/Information Sciences Institute

   "Resolving Translation Ambiguity using Non-parallel Bilingual Corpora"
   Genichiro Kikui, NTT Cyberspace Laboratories

12:10-1:30 Lunch

1:30-3:00 Paper Session II

   "Detecting Sub-Topic Correspondence through Bipartite Term Clustering"
   Zvika Marx, Ido Dagan, and Eli Shamir, The Hebrew University of Jerusalem and Bar-Ilan University

   "Text Classification by Bootstrapping with Keywords, EM and Shrinkage"
   Andrew McCallum and Kamal Nigam, Just Research and Carnegie Mellon University

   "Hiding a Semantic Hierarchy in a Markov Model"
   Steven Abney and Marc Light, AT&T Labs and the MITRE Corporation

3:00-4:00 INVITED TALK: Michael Brent, Johns Hopkins University

   "Combinatoric Generative Models: Bridging the Gap from Minimum Description Length to Complete Probability Models"


4:00-4:20 Coffee Break

4:20-5:50 Paper Session III

   "The Applications of Unsupervised Learning to Japanese Grapheme-Phoneme Alignment"
   Timothy Baldwin and Hozumi Tanaka, Tokyo Institute of Technology

   "Unsupervised Lexical Learning with Categorial Grammars" 
   Stephen Watkinson and Suresh Manandhar, University of York

   "Unsupervised Learning of Derivational Morphology from Inflectional Lexicons"
   Eric Gaussier, Xerox Research Centre Europe

5:50-6:30 Panel Session on Unsupervised Learning in NLP

   Eric Brill, Johns Hopkins University
   John Lafferty, Carnegie-Mellon University
   Andrew McCallum, Carnegie-Mellon University and Just Research
   Janyce Wiebe, New Mexico State University