|
|
Cover |
| page I |
|
|
Brief Contents |
| page III |
|
|
Greeting from the General Chair |
| Jun'ichi Tsujii (University of Tokyo, Japan) | |
| page V |
|
|
Message from the Program Chair |
| Keh-Yih Su (Behavior Design Corperation, Taiwan) | |
| page VII |
|
|
Message from the Local Organization Chair |
| Hiroshi Nakagawa (University of Tokyo, Japan) | |
| page IX |
|
|
Committees |
| page XI |
|
|
Table of Contents |
| page XV |
|
|
Audio Browsing and Search in the Voicemail Domain |
| Julia Hirschberg (AT&T Labs-Research, USA), Michiel Bacchiani and Phil Isenhour | |
| pages 3-8 |
|
|
Corpus, Information Mining and the New Global Village |
| Benjamin K. Tsou (City University of Hong Kong, Hong Kong SAR) | |
| pages 9-18 |
|
|
From Read Speech Recognition to Spontaneous Speech Understanding |
| Sadaoki Furui (Tokyo Institute of Technology, Japan) | |
| pages 19-25 |
|
|
Just-In-Time Question Answering |
| Sanda M. Harabagiu (University of Texas, USA) | |
| pages 27-34 |
|
|
Are NLP technologies really ready for application? |
| Jun'ichi Tsujii (Organizer; University of Tokyo, Japan) | |
| pages 37-38 |
|
|
Ensembling based on Feature Space Restructuring with Application to WSD |
| Hiroya Takamura, Hiroyasu Yamada, Taku Kudoh, Kaoru Yamamoto and Yuji Matsumoto | |
| pages 41-48 |
|
|
Word Sense Disambiguation Using Vectors of Co-occurrence Information |
| Saim Shin, Yong-soek Choi and Key-Sun Choi | |
| pages 49-55 |
|
|
A Bayesian Approach to Semi-Supervised Learning |
| Rebecca Bruce | |
| pages 57-64 |
|
|
Disambiguation of Compound Noun Translations Extracted from Bilingual Comparable Corpora |
| Hiroshi Nakagawa | |
| pages 67-74 |
|
|
Word Sense Disambiguation with a Corpus-Based Semantic Network |
| Qujiang Peng, Takeshi Ito and Teiji Furugori | |
| pages 75-82 |
|
|
Automatic Sense Tagging Using Parallel Corpora |
| Nancy Ide, Tomaž Erjavec and Dan Tufis | |
| pages 83-90 |
|
|
Evaluating Automatic Text Summarization with Summary Results by the Experienced and the Inexperienced |
| Kai Ishikawa, Shinichi Ando and Akitoshi Okumura | |
| pages 93-100 |
|
|
Analysis of Linguistic Features for Identifying Information Constituents of a Concept |
| Haeseung Paik, Young-Soo Kang and Key-Sun Choi | |
| pages 101-107 |
|
|
WordNet and Automated Text Summarization |
| Rui Pedro Chaves | |
| pages 109-116 |
|
|
Papillon Lexical Database Project: Monolingual Dictionaries & Interlingual Links |
| Gilles Sérasset and Mathieu Mangeot | |
| pages 119-125 |
|
|
Relative Synonymy and Conceptual Vectors |
| Matthieu Lafourcade and Violaine Prince | |
| pages 127-134 |
|
|
Integration of heterogeneous language resources: A monolingual dictionary and a thesaurus |
| Takenobu Tokunaga, Yasuhiro Syotu, Hozumi Tanaka and Kiyoaki Shirai | |
| pages 135-142 |
|
|
A Simple Closed-Class/Open-Class Factorization for Improved Language Modeling |
| Fuchun Peng and Dale Schuurmans | |
| pages 145-152 |
|
|
Learning Strategies In A Grammar Induction Framework |
| Chin-Chung Wong, Helen Meng and Kai-Chung Siu | |
| pages 153-157 |
|
|
Corpus-Based Acquisition of Sentence Readability Ranking Models for Deaf People |
| Kentaro Inui and Satomi Yamamoto | |
| pages 159-166 |
|
|
A New Prosodic Phrasing Model for Chinese TTS Systems |
| Weijun Chen, Fuzong Lin, Jianmin Li and Bo Zhang | |
| pages 169-175 |
|
|
Personalization of Text Entry Systems for Mobile Phones |
| Kumiko Tanaka-Ishii, Yusuke Inutsuka and Masato Takeichi | |
| pages 177-184 |
|
|
Enhancing the Robustness of DOP for Speech Understanding |
| Khalil Sima'an | |
| pages 185-192 |
|
|
Paraphrasing Utterances by Reordering Words Using Semi-Automatically Acquired Patterns |
| Yujie Zhang, Kazuhide Yamamoto, Chengqing Zong and Masashi Sakamoto | |
| pages 195-202 |
|
|
Paraphrasing Spoken Japanese for Untangling Bilingual Transfer |
| Kazuhide Yamamoto | |
| pages 203-210 |
|
|
An Unsupervised Method for Canonicalization of Japanese Postpositions |
| Kentaro Torisawa | |
| pages 211-218 |
|
|
Re-interpretation of Rules for Named Entity Task by Probability Assignment |
| Tatsunori Mori | |
| pages 221-228 |
|
|
Named Entity Recognition using Machine Learning Methods and Pattern-Selection Rules |
| Choong-Nyoung Seon, Youngjoong Ko, Jeong-Seok Kim and Jungyun Seo | |
| pages 229-236 |
|
|
An Efficient Method for Korean Noun Extraction Using Noun Occurrence Characteristics |
| Do-Gil Lee, Sang-Zoo Lee and Hae-Chang Rim | |
| pages 237-244 |
|
|
A Case Study of Free Word Order Grammar Development in DG, TAG and LFG |
| Mark Pedersen and Helen Purchase | |
| pages 247-254 |
|
|
A Separate-and-Learn Approach to EM Learning of PCFGs |
| Taisuke Sato, Shigeru Abe, Yoshitaka Kameya and Kiyoaki Shirai | |
| pages 255-262 |
|
|
Resolving Ambiguity in Inter-chunk Dependency Parsing |
| Mi-Young Kim, Sin-Jae Kang and Jong-Hyeok Lee | |
| pages 263-270 |
|
|
Topic Segmentation : A First Stage to Dialog-Based Information Extraction |
| Narjes Boufaden, Guy Lapalme and Yoshua Bengio | |
| pages 273-279 |
|
|
kNN vs. Linear Support Vector Machine in Event Tracking |
| Weiquan Liu and Joe F Zhou | |
| pages 281-288 |
|
|
Topic-Word Selection Based on Combinatorial Probability |
| Toru Hisamitsu and Yoshiki Niwa | |
| pages 289-296 |
|
|
Hierarchical Concept Description and Learning for Information Extraction |
| Luo Xiao, Dieter Wissmann, Michael Brown and Stefan Jablonski | |
| pages 299-306 |
|
|
Linguistic Techniques to Improve the Performance of Automatic Text Categorization |
| Akiko Aizawa | |
| pages 307-314 |
|
|
Classification of Open-Ended Questionnaires based on Surface Information in Sentence Structure |
| Hiroko Inui, Masaki Murata, Kiyotaka Uchimoto and Hitoshi Isahara | |
| pages 315-322 |
|
|
Unknown Word Guessing and Part-of-Speech Tagging Using Support Vector Machines |
| Tetsuji Nakagawa, Taku Kudoh and Yuji Matsumoto | |
| pages 325-331 |
|
|
A Maximum Entropy Tagger with Unsupervised Hidden Markov Models |
| Jun'ichi Kazama, Yusuke Miyao and Jun'ichi Tsujii | |
| pages 333-340 |
|
|
Partially Supervised Learning of Morphology with Stochastic Transducers |
| Alexander Clark | |
| pages 341-348 |
|
|
Incremental CFG Parsing with Statistical Lexical Dependencies |
| Takahisa Murase, Shigeki Matsubara, Yoshihide Kato and Yasuyoshi Inagaki | |
| pages 351-358 |
|
|
GLR Parser with Conditional Action Model(CAM) |
| Yong-Jae Kwak, Young-Sook Hwang, Hoo-Jung Chung, So-Young Park, Sang-Zoo Lee and Hae-Chang Rim | |
| pages 359-366 |
|
|
Abstract Left-corner Parsing for Unification Grammars |
| Noriko Tomuro and Steven L. Lytinen | |
| pages 367-374 |
|
|
Hierarchical Phrase Alignment Harmonized with Parsing |
| Kenji Imamura | |
| pages 377-384 |
|
|
Segmented LSI for Fully Automated Large-scale Cross-Language Information Retrieval |
| Tatsunori Mori | |
| pages 385-392 |
|
|
Automatically Harvesting Katakana-English Term Pairs from Search Engine Query Logs |
| Eric Brill, Gary Kacmarcik and Chris Brockett | |
| pages 393-399 |
|
|
A Probabilistic Model for Japanese Zero Pronoun Resolution Integrating Syntactic and Semantic Features |
| Kazuhiro Seki, Atsushi Fujii and Tetsuya Ishikawa | |
| pages 403-410 |
|
|
Discovery of Definition Patterns by Compressing Dictionary Sentences |
| Masatoshi Tsuchiya, Sadao Kurohashi and Satoshi Sato | |
| pages 411-418 |
|
|
Korean Text Generation from Database for Homeshopping Sites |
| Ji-Eun Roh, Sin-Jae Kang and Jong-Hyeok Lee | |
| pages 419-426 |
|
|
Japanese Information Retrieval Method Using Syntactic and Statistical Information |
| Tsunenori Mine, Hiroki Fujitani and Makoto Amamiya | |
| pages 429-434 |
|
|
Migemo: Incremental Search Method for Languages with Many Character Faces |
| Satoru Takabayashi, Hiroyuki Komatsu and Toshiyuki Masui | |
| pages 435-438 |
|
|
Language Independent Text Categorization |
| Huang Xuanjing, Wu Lide, Xu Guowei and Hiroyuli Ishizaki | |
| pages 441-446 |
|
|
Acquisition of Sentence Reduction Rules for Improving Quality of Text Summaries |
| Kazuhiro Takeuchi and Yuji Matsumoto | |
| pages 447-452 |
|
|
Finding Target Language Correspondence for Lexicalized EBMT System |
| Wei Wang, Jin-Xia Huang, Ming Zhou and Chang-Ning Huang | |
| pages 455-460 |
|
|
Generation of 3D CG Animations from Recipe Sentences |
| Hideki Uematsu, Akira Shimazu and Manabu Okumura | |
| pages 461-466 |
|
|
A Usability Case Study of Grammar Formalisms for Free Word Order Natural Language Processing |
| Mark Pedersen and Helen Purchase | |
| pages 469-474 |
|
|
A Hierarchical EM Approach to Word Segmentation |
| Fuchun Peng and Dale Schuurmans | |
| pages 475-480 |
|
|
Statistical Parsing of Dutch using Maximum Entropy Models with Feature Merging |
| Tony Mullen, Rob Malouf and Gertjan van Noord | |
| pages 481-486 |
|
|
Harmonised Morphosyntactic Tagging for Seven Languages and Orwell's 1984 |
| Tomaž Erjavec | |
| pages 487-492 |
|
|
Grapheme-to-Phoneme for Thai |
| Pongthai Tarsaku, Virach Sornlertlamvanich and Rachod Thongprasirt | |
| pages 493-498 |
|
|
Application and Difficulty of Natural Language Processing in Chinese Temporal Information Extraction |
| Wenjie Li, Kam-Fai Wong and Chunfa Yuan | |
| pages 501-506 |
|
|
Modality Expressions in Japanese and Their Automatic Paraphrasing |
| Toshifumi Tanabe, Kenji Yoshimura and Kosho Shudo | |
| pages 507-512 |
|
|
Analysis and Reconstrution of Dictionary Definition Units |
| Chung-Won Seo and Key-Sun Choi | |
| pages 513-518 |
|
|
Improving accuracy in Base Noun Phrase Identification with the variation of context length and position |
| In-Ho Kang, Yeojin Lee and GilChang Kim | |
| pages 519-524 |
|
|
A Modular Approach to Turkish Noun Compounding: The Integration of a Finite-State Model |
| Aysenur Akyuz Birturk and Sandiway Fong | |
| pages 525-530 |
|
|
A summary planner based on a three-level discourse model |
| Thiago Alexandre Salgueiro Pardo and Lucia Helena Machado Rino | |
| pages 533-538 |
|
|
Pruning UNL texts for Summarizing Purposes |
| Camilla Brandel Martins and Lucia Helena Machado Rino | |
| pages 539-544 |
|
|
Design of a Generation Component for a Spoken Dialogue System |
| Graham Wilcock and Kristiina Jokinen | |
| pages 545-550 |
|
|
Approach to Spoken Chinese Paraphrasing Based on Feature Extraction |
| Chengqing Zong, Yujie Zhang, Kazuhide Yamamoto, Masashi Sakamoto and Satoshi Shirai | |
| pages 551-556 |
|
|
Centering as an Anaphora Generation Algorithm: A Language Learning Aid Perspective |
| Mitsuko Yamura-Takei, Miho Fujiwara and Teruaki Aizawa | |
| pages 557-562 |
|
|
Speaker Determination in Video News by Using Acoustic Features and Transcripts |
| Yasuhiko Watanabe, Shigeru Toji and Yoshihiro Okada | |
| pages 565-570 |
|
|
Cross-Language Information Retrieval of Proper Nouns using Context Information |
| Isao Goto, Noriyoshi Uratani and Terumasa Ehara | |
| pages 571-578 |
|
|
Thai Text Entry with Digits |
| Yusuke Inutsuka, Kumiko Tanaka-Ishii and Masato Takeichi | |
| pages 579-584 |
|
|
Sentence Extraction by Questioning |
| Zenshiro Kawasaki, Keiji Shibata and Masato Tajima | |
| pages 585-591 |
|
|
Summarizing Newspaper Articles Using Extracted Informative and Functional Words |
| Mamiko Hatayama, Yoshihiro Matsuo and Satoshi Shirai | |
| pages 593-600 |
|
|
Monologue Summarization: Extraction of Important Sentences for TV News Commentary Programs |
| Takahiro Ito, Kenji Matsumoto, Yasuo Tanida, Hideki Kashioka and Hideki Tanaka | |
| pages 601-608 |
|
|
A E-mail Filtering System Based on Personal Profiles |
| Masami Shishibori, Kazuaki Ando and Jun-ichi Aoe | |
| pages 609-616 |
|
|
Multilingual Document Alignment - A Study with Chinese and Japanese |
| Md Maruf Hasan and Yuji Matsumoto | |
| pages 617-623 |
|
|
Acquiring word meanings with questions,answers and a dynamic environment - generalizing with neural networks. |
| Mats U. Nystrand, Naoto Takahashi and Kazuhiro Ueda | |
| pages 625-630 |
|
|
Usability Word-Pair Features for Probabilistic Text Classifiers |
| Sang-Bum Kim, Gum-Won Hong, Sang-Zoo Lee, Hae-Chang Rim and Myoung-Sook Ko | |
| pages 631-638 |
|
|
Korean to English TV Caption Translator: ""CaptionEye/KE"" |
| Seong-il Yang, Young-Kil Kim, Young-Ae Seo, Sung-Kwon Choi and Sang-Kyu Park | |
| pages 639-645 |
|
|
Long Sentence Partitioning using Structure Analysis for Machine Translation |
| Yoon-Hyung Roh, Young-Ae Seo, Ki-Young Lee and Sung-Kwon Choi | |
| pages 646-652 |
|
|
Headline Generation for Summaries from Multiple Online Sources |
| Hong-Jia Wong, June-Jei Kuo and Hsin-Hsi Chen | |
| pages 653-660 |
|
|
Use of a Lexical Feature Database for Partial Parsing of Chinese |
| Elliott Franco Drábex and Qiang Zhou | |
| pages 663-668 |
|
|
Automatic Corpus-Based Extraction of Chinese Legal Terms |
| Oi Yee Kwong and Benjamin K. Tsou | |
| pages 669-676 |
|
|
Span-based Statistical Dependency Parsing of Chinese |
| Tom B.Y. Lai, Chang-Ning Huang, Ming Zhou, Jiangbo Miao and Tony K.C. Siu | |
| pages 677-684 |
|
|
Unsupervised Improvement of Morphological Analyzer for Inflectionally Rich Languages |
| Akshar Bharati, Rajeev Sangal, Sushma Bendre, Pavan Kumar and Aishwarya | |
| pages 685-692 |
|
|
Chunking with Decision Trees |
| Dirk Lüdtke | |
| pages 693-699 |
|
|
Estimating Reliability of Contextual Evidences in Decision-List Classifiers under Bayesian Learning |
| Yoshimasa Tsuruoka and Takashi Chikayama | |
| pages 701-707 |
|
|
The Grammatical Function Analysis between Adnoun Clause and Noun Phrase in Korean |
| Songwook Lee, Tae-Yeoub Jang and Jungyun Seo | |
| pages 709-713 |
|
|
Word Sense Disambiguation Using Neural Networks with Concept Co-occurrence Information |
| You-Jin Chung, Sin-Jae Kang, Kyoung-Hi Moon and Jong-Hyeok Lee | |
| pages 715-722 |
|
|
Korean Adverb Ordering in English-Korean Machine Translation Using Clustering |
| Shin Won Lee, Dong Un An and Seong Jong Chung | |
| pages 723-728 |
|
|
Automatic Segmentation of Words using Syllable Bigram Statistics |
| Seung-Shik Kang and Chong-Woo Woo | |
| pages 729-732 |
|
|
An Empirical Study of Feature Set Selection for Text Chunking |
| Young-Sook Hwang, Yong-Jae Kwak, Hoo-Jung Chung, So-Young Park and Hae-Chang Rim | |
| pages 733-740 |
|
|
Efficient Parsing for Word Structure |
| Anna Maria Di Sciullo and Sandiway Fong | |
| pages 741-748 |
|
|
Vietnamese Word Segmentation |
| Dinh Dien, Hoang Kiem and Nguyen Van Toan | |
| pages 749-756 |
|
|
A Korean Language Processing Workbench |
| Key-Sun Choi | |
| pages 759-760 |
|
|
SummaryBIFF: An E-mail Summarizer for Mobile Phones |
| Takaaki Hasegawa, Takefumi Yamazaki and Yoshihiko Hayashi | |
| pages 761-762 |
|
|
Kura: A Lexico-Structural Paraphrasing Engine |
| Ryu Iida, Kentaro Inui, Tomoya Iwakura, Atsushi Fujita and Tetsuro Takahashi | |
| pages 763-764 |
|
|
LiLFeS/GENIA Project --- NLP Tools and A Biology Domain Corpus --- |
| Jun'ichi Tsujii | |
| pages 765-766 |
|
|
XML Transformation-based three-stage pipelined Natural Language Generation System |
| Yohei Seki | |
| pages 767-768 |
|
|
Collaborative Translation Environment `Yakushite.Net' |
| Tatsuya Sukehiro, Mihoko Kitamura and Toshiki Murata | |
| pages 769-770 |
|
|
Associative information access using DualNAVI |
| Akihiko Takano, Yoshiki Niwa, Shingo Nishioka, Toru Hisamitsu, Makoto Iwayama and Osamu Imaichi | |
| pages 771-772 |
|
|
Text Mining and Site Outlining Projects |
| Koichi Takeda, Hiroshi Nomiyama, Tetsuya Nasukawa, Mei Kobayashi, Takashi Sakairi, Hirofumi Matsuzawa, Tohru Nagano, Akiko Murakami and Hironori Takeuchi | |
| pages 773-774 |
|
|
JSPS project: Natural Language Understanding and Action Control |
| Hozumi Tanaka | |
| pages 775-776 |
|
|
AZALEA: A KE-Free ICALL (intelligent computer assisted language learning) System for Japanese-English Translation |
| Naoyuki Tokuda, L.iang Chen and Qing Zhong | |
| pages 777-778 |
|
|
Tools for Exploring Natural Language |
| Masao Utiyama and Hitoshi Isahara | |
| pages 779-780 |
|
|
Text Entry/Conversion Systems for Mobile Phones |
| Toshihiko Watanabe, Yusuke Inutsuka, Kumiko Tanaka-Ishii and Hiroshi Nakagawa | |
| pages 781-782 |
|
|
Author Index |
| pages 785-787 |