EMNLP Preliminary Program

On-site registration is outside the Connan Room; talks are in McConomy Auditorium, on the first floor of the University Center.

8:45 9:00 Welcome
Session I: Learning
9:00 9:25 Limitations of Co-Training for Natural Language Learning from Large Datasets
David Pierce and Claire Cardie
9:25 9:50 A Sequential Model for Multi-Class Classification
Yair Even-Zohar and Dan Roth
9:50 10:15 Learning Within-Sentence Semantic Coherence
Elena Eneva, Rose Hoberman and Lucian Lita
10:15 10:45 Break
Session II: Machine Translation
10:45 11:10 Knowledge Sources for Word-Level Translation Models
Philipp Köhn and Kevin Knight
11:10 11:35 Improving Lexical Mapping Model of English-Korean Bitext Using Structural Features
Seonho Kim, Juntae Yoon and Mansuk Song
11:35 11:45 Short break
11:45 12:45 Invited talk, Eric Brill
"Paucity Shmaucity -- What Can We Do With A Trillion Words?"
12:45 2:00 LUNCH
Session III: Text Categorization
2:00 2:25 Stacking Classifiers for Anti-Spam Filtering of E-Mail
Georgios Sakkis, Ion Androutsopoulos, Georgios Paliouras, Vangelis Karkaletsis, Constantine D. Spyropoulos and Panagiotis Stamatopoulos
2:25 2:50 Feature Space Restructuring for SVMs with Application to Text Categorization
Hiroya Takamura and Yuji Matsumoto
2:50 3:15 Using Bins to Empirically Estimate Term Weights for Text Categorization
Carl Sable and Kenneth W. Church
3:15 3:25 Short break
Session IV: Question Answering and Information Extraction
3:25 3:50 Question Answering Using a Large Text Database: A Machine Learning Approach
Hwee Tou Ng, Jennifer Lai Pheng Kwan and Yiyuan Xia
3:50 4:15 Information Extraction Using the Structured Language Model
Ciprian Chelba and Milind Mahajan
4:15 4:30 Short break
4:30 5:30 Panel: When does EM work? (includes an introduction to the Expectation-Maximization algorithm)
Eugene Charniak, Kevin Knight, Ted Pedersen, Stefan Riezler

Session V: Lexical Acquisition and Text Segmentation
8:35 9:00 Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy
Barbara Rosario and Marti Hearst
9:00 9:25 The Unknown Word Problem: a Morphological Analysis of Japanese Using Maximum Entropy Aided by a Dictionary
Kiyotaka Uchimoto, Satoshi Sekine and Hitoshi Isahara
9:25 9:50 Is Knowledge-Free Induction of Multiword Unit Dictionary Headwords a Solved Problem?
Patrick Schone and Daniel Jurafsky
9:50 10:15 Latent Semantic Analysis for Text Segmentation
Freddy Y. Y. Choi, Peter Wiemer-Hastings and Johanna Moore
10:15 10:45 Break
Session VI: Applications
10:45 11:10 Detecting Short Passages of Similar Text in Large Document Collections
Caroline Lyon, James Malcolm and Bob Dickerson
11:10 11:35 Hybrid Text Mining for Finding Abbreviations and their Definitions
Youngja Park and Roy J. Byrd
11:35 11:45 Short break
11:45 12:45 Panel: What Works and What Doesn't? Industrial Perspectives
Adam Berger, David Evans, Joshua Goodman, Lynette Hirschman
12:45 2:00 LUNCH
Session VII: Spoken Language Output
2:00 2:25 Automatic Corpus-based Tone Prediction using K-ToBI Representation
Jin-Seok Lee, Byeongchang Kim and Gary Geunbae Lee
2:25 2:50 Probabilistic Context-Free Grammars for Syllabification and Grapheme-to-Phoneme Conversion
Karin Müller
2:50 3:00 Short break
Session VIII: POS Tagging and Corpus Analysis
3:00 3:25 Comparing Data-Driven Learning Algorithms for PoS Tagging of Swedish
Beáta Megyesi
3:25 3:50 Impact of Quality and Quantity of Corpora on Stochastic Generation
Srinivas Bangalore, John Chen and Owen Rambow
3:50 4:15 Corpus Variation and Parser Performance
Daniel Gildea
4:15 4:30 Refreshments (close)

Note: the formatting of this page comes from the version generated for the NAACL CDROM.