VERY LARGE CORPORA

                             October 7-8, 2000
               Hong Kong University of Science and Technology

Saturday, October 7

8:45-9:00      REGISTRATION

9:00-9:05      WELCOME

9:05-9:30      Pattern-Based Disambiguation for Natural Language Processing
               Eric Brill

9:30-9:55      What's yours and what's mine: Determining Intellectual
                Attribution in Scientific Text
               Simone Teufel and Marc Moens

9:55-10:20     Japanese Dependency Structure Analysis Based
                on Support Vector Machines
               Taku Kudo and Yuji Matsumoto

10:20-10:45    Coaxing Confidences from an Old Friend: Probabilistic
                Classifications from Transformation Rule Lists
               Radu Florian, John Henderson and Grace Ngai

10:45-11:05    BREAK

11:05-12:15    INVITED SPEAKER
               John B. Lowe, VP of Language Engineering, Ask Jeeves Inc.
               What's in store for question answering?
               Prognostications based on corpus analysis
                of several hundred million questions

12:15-13:30    LUNCH

13:30-13:55    A Real-time Integration Of Concept-based
                Search and Summarization of Chinese Websites
               Joe Zhou and Weiqian Liu

13:55-14:20    Topic Analysis Using a Finite Mixture Model
               Hang Li and Kenji Yamanishi

14:20-14:45    A Uniform Method of Grammar Extraction and Its Applications
               Fei Xia, Martha Palmer and Aravind Joshi

14:45-15:00    BREAK

15:00-15:25    Enriching the Knowledge Sources Used in a
                Maximum Entropy Part-of-Speech Tagger
               Kristina Toutanova and Christopher D. Manning

15:25-15:50    Error-driven HMM-based Chunk Tagger
                with Context-dependent Lexicon
               GuoDong Zhou and Jian Su

15:50-16:15    Nonlocal Language Modeling based on
                Context Co-occurrence Vectors
               Sadao Kurohashi and Manabu Ori

16:15-16:40    Detection of Language (Model) Errors
               K.Y. Hung, R.W.P. Luk, D. Yeung, K.F.L. Chung and W. Shu

16:40-17:00    BREAK

17:00-17:25    Cross-lingual Information Retrieval
                Using Hidden Markov Models
               Jinxi Xu and Ralph Weischedel

17:25-17:50    Query Translation in Chinese-English
                Cross-Language Information Retrieval
               Yibo Zhang, Le Sun, Lin Du and Yufang Sun

17:50-18:15    Word Alignment of English-Chinese Bilingual Corpus
                Based on Chunks
               Le Sun, Youbing Jin, Lin Du and Yufang Sun

18:15-18:40    Empirical Term Weighting and Expansion Frequency
               Kyoji Umemura and Kenneth W. Church

Sunday, October 8

9:00-9:25      Sample Selection for Statistical Grammar Induction
               Rebecca Hwa

9:25-9:50      A Statistical Model for Parsing and Word-Sense Disambiguation
               Daniel M. Bikel

9:50-10:15     Reducing Parsing Complexity by Intra-Sentence
                Segmentation based on Maximum Entropy Model
               Sung Dong Kim and Byoung Tak Zhang

10:15-10:40    An Empirical Study of the Domain Dependence
                of Supervised Word Sense Disambiguation Systems
               Gerard Escudero, Lluis Marquez and German Rigau

10:40-11:00    BREAK

11:00-12:00    INVITED SPEAKER
               Soumen Chakrabarti, Indian Institute of Technology
               Nurturing content-based collaborative communities on the Web

12:00-13:20    LUNCH

13:20-14:35    PANEL DISCUSSION
               NLP for the Web: Critical Technology or Luxury?
               Ken Church, AT&T Labs
               John Lowe, Ask Jeeves
               Drago Radev, University of Michigan
               Joe Zhou, Intel China Research Center

14:35-15:00    A Machine Learning Approach to Answering Questions
                for Reading Comprehension Tests
               Hwee Tou Ng, Leong Hwee Teo and Jennifer Lai Pheng Kwan

15:00-15:25    Automated Construction of Database Interfaces: Integrating
                Statistical and Relational Learning for Semantic Parsing
               Lappoon R. Tang and Raymond J. Mooney

15:25-15:50    Automatic WordNet Mapping Using Word Sense Disambiguation
               Changki Lee, Geunbae Lee and Seo Jung Yun

15:50-16:10    BREAK

16:10-16:35    Combining Lexical and Formatting Cues for Named Entity
               Christian Jacquemin and Caroline Bush

16:35-17:00    A Query Tool for Syntactically Annotated Corpora
               Laura Kallmeyer

17:00-17:25    Statistical Filtering and Subcategorization Frame Acquisition
               Anna Korhonen, Genevieve Gorrell and Diana McCarthy

17:25-17:50    One Sense per Collocation and Genre/Topic Variations
               David Martinez and Eneko Agirre