nil image
Joint conference of the 47th Annual Meeting of the Association for Computational Linguistics and
the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing

Program -WS7

Second Workshop on Building and Using Comparable Corpora: from Parallel to Non-parallel Corpora

Thursday, August 6, 2009

8:45 Welcome and Introduction
  Invited Presentation
9:00 Repetition and Language Models and Comparable Corpora
Ken Church
10:00 Coffee break
  Information Extraction and Summarization
10:30 Extracting Lay Paraphrases of Specialized Expressions from Monolingual Comparable Medical Corpora
Louise Deléger and Pierre Zweigenbaum
10:55 An Extensible Crosslinguistic Readability Framework
Jesse Kirchner, Justin Nuger and Yi Zhang
11:20 An Analysis of the Calque Phenomena Based on Comparable Corpora
Marie Garnier and Patrick Saint-Dizier
11:45 Active Learning of Extractive Reference Summaries for Lecture Speech Summarization
Jian Zhang and Pascale Fung
12:10 Lunch break
  Statistical Machine Translation
13:50 Train the Machine with What It Can Learn—Corpus Selection for SMT
Xiwu Han, Hanzhang Li and Tiejun Zhao
14:15 Mining Name Translations from Comparable Corpora by Creating Bilingual Information Networks
Heng Ji
14:40 Chinese-Uyghur Sentence Alignment: An Approach Based on Anchor Sentences
Samat Mamitimin and Min Hou
15:05 Exploiting Comparable Corpora with TER and TERp
Sadaf Abdul Rauf and Holger Schwenk
15:30 Coffee break
  Building Comparable Corpora
16:00 Compilation of Specialized Comparable Corpora in French and Japanese
Lorraine Goeuriot, Emmanuel Morin and Béatrice Daille
16:25 Toward Categorization of Sign Language Corpora
Jérémie Segouat and Annelies Braffort
16:50 Panel Session
Multilingual Information Processing: from Parallel to Comparable Corpora
17:50 End of Workshop


Copyright © 2008-2009 Chinese and Oriental Languages Information Processing Society