Fifth Workshop On Very Large Corpora
(WVLC-5)

Final Call For Participation

First session: Tsinghua University, Beijing, China, August 18, 1997 (In conjunction with JSCL'97: the Fourth Joint Symposium of Computational Linguistics of China)

Second session: Hong Kong University of Science and Technology (HKUST), Hong Kong, China, August 20, 1997

Except for the following updates and changes, see First Call for Participation.

Contents

Beijing

Final Program
Guest Speakers
Panelists
Beijing Poster Sessions

Hong Kong

Final Program
Guest Speakers
Panelists

Contact

Final Program - Beijing

August 18, 1997 - Tsinghua University, Beijing, China

TIME PRESENTER - SUBJECT
8:30 - 8:45 Opening
8:45 - 9:10 Qiang Zhou
A Statistics-based Chinese Parser
9:10 - 9:35 Thanaruk Theeramunkong and Manabu Okumura
Grammar Acquisition based on Clustering Analysis and its Application to Statistical parsing
9:35 - 10:00 Seungmi Lee and Key-Sun Choi
Reestimation and Best First Parsing Algorithms for Probabilistic Dependency Grammar
10:00 - 10:30 Break See Poster Sessions
10:30 - 10:55 Tomek Strzalkowski and Ron Brandow
A Natural Language Correction Model for Continuous Speech Recognition
10:55 - 11:20 Masaaki Nagata
A Self-Organizing Japanese Word Segmenter using Heuristic Word Identification and Re-estimation
11:20 - 12:20 Mitch Marcus
Invited Talk
12:20 - 2:20 Lunch
2:20 - 2:45 Hiromi Nakaiwa
Automatic identification of zero pronouns and their antecedent within aligned sentence pairs
2:45 - 3:10 Xuan-jing Huang, Li-de Wu and Wen-xin Wang
Statistical Acquisition of Terminology Dictionary
3:10 - 4:10 John Rausch
Invited Talk
4:10 - 4:40 Break
4:40 - 5:40 Panel Discussion
Innovative Uses and Applications of Large Corpora
5:40 - 6:05 Kumiko Tanaka-Ishii and Hideya Iwasaki
Clustering Co-occurrence Graph Based on Transitivity
6:05 - 6:30 Sta Jean-David
Knowledge Acquisition : Classification of terms in a thesaurus from a corpus
6:30 - 6:40 Closing

Guest Speakers - Beijing

Mitch Marcus, ACL President and Chairman of Department of Compute Information Science, University of Pennsylvania

John Rausch, Chief Technologist, LEXIS-NEXIS, a Division of Reed Elsevier

Panelists - Beijing

Mitch Marcus, ACL President and Chairman of Department of Compute Information Science, University of Pennsylvania

John Rausch, Chief Technologist, LEXIS-NEXIS, a Division of Reed Elsevier

Howard Turtle, Chief Scientist, West Group

Tomel Strzalkowski, GE R&D Corporarion, Albany, USA

Ezra Black, ATR Laboratories, Kyoto, Japan

Benjamin Tsou, City University of Hong Kong, Hong Kong

Changning Huang, Tsinghua University, Beijing, China

Beijing Poster Sessions (During break and lunch times)

Takehito Utsuro, Takashi Miyata and Yuji Matsumoto
Maximum Entropy Model Learning of Subcategorization Preference
 
Scott M. Thede and Mary Harper
Identifying Unknown Lexical Items using Morphological and Syntactic Information using the TIMIT Corpus
 
Jee-sun Nam and Key-sun Choi
LG-based Approach to Recognizing proper names in Korean
 
Asanee Kawtrakul, Chalatip Thumkanon
A Statistical Approach to Thai Morphological Analzer
 
Jun Gao and Xi-Xian Chen
Probalistic Word Classification Base on Context-Sensitive Binary Tree Method

Fianl Program - Hong Kong

August 20, 1997 - Hong Kong University of Sceience and Technology, Hong Kong

TIME PRESENTER - SUBJECT
8:30 - 8:45 Opening
8:45 - 9:10 Li Shiuan Peh and Hwee Tou Ng
Domain-Specific Semantic Class Disambiguation using WordNet
9:10 - 9:35 Jiri Stetina and Makoto Nagao
Corpus-based PP Attachment Ambiguity Resolution with a Semantic Dictionary
9:35 - 10:00 Joyce Yue Chai and Alan W. Biermann
Corpus Based Statistical Generalization Tree in Rule Optimization
10:00 - 10:30 Break
10:30 - 10:55 E. Black, S. Eubank and K. Kashioka
Probabilistic Parsing of Unrestricted English Text, With A Highly-Detailed Grammar
10:55 - 11:20 T. Rose, N. Haddock and R. Tucker
The effects of corpus size and homogeneity on language model quality
11:20 - 12:20 Mitch Marcus
Invited Talk
12:20 - 2:00 Lunch
2:00 - 2:25 Erika F. de Lima
Acquiring German Prepositional Subcategorization Frames from Corpora
2:25 - 2:50 Pascale Fung and Kathleen McKeown
Finding Terminology Translations from Non-Parallel Corpora
2:50 - 3:50 Howard Turtle
Invited Talk
3:50 - 4:20 Break
4:20 - 5:25 Panel Discussion
Innovative Uses and Applications of Large Corpora
5:25 - 5:50 Tadashi Nomoto and Yuji Matsumoto
Data Reliability and its Effects on Automatic Abstracting
5:50 - 6:15 Andrei Mikheev
Collocation Lattices and Maximum Entropy Models
6:15 - 6:25 Closing

Guest Speakers - Hong Kong

Mitch Marcus, ACL President and Chairman of Department of Compute Information Science, University of Pennsylvania

Howard Turtle, Chief Scientist, West Group

Panelists - Hong Kong

Mitch Marcus, ACL President and Chairman of Department of Compute Information Science, University of Pennsylvania

John Rausch, Chief Technologist, LEXIS-NEXIS, a Division of Reed Elsevier

Howard Turtle, Chief Scientist, West Group

Kui Kam Kwok, Queens College, City University of New York, USA

Dekai Wu, The Hong Kong University of Science and Technology, Hong Kong

Keh-Yh Su, National Tsinghua University, Taiwan

Eva Ejerhed, University of Umea, Sweden

Contact:

Joe Zhou
LEXIS-NEXIS, a Division of Reed Elsevier
9555 Springboro Pike
Dayton, OH 45342 USA
joez@lexis-nexis.com
   
  Ken Church
Room 2B-421
AT&T Laboratories
Murray Hill, NJ 07974 USA
kwc@research.att.com