The 1st International Joint Conference on Natural Language Processing organized by the Asia Federation of NLP associations (AFNLP)

Website:
http://www.rcl.cityu.edu.hk/ijcnlp04
http://www.colips.org/conference/ijcnlp04/ (mirror site in Singapore)
http://www.isi.edu/natural-language/ijcnlp04 (mirror site at USC)
http://www.cipsc.org.cn/IJCNLP-04/
************************************************************************
[Date]
Main Conference: March 22-24, 2004
Workshops/symposium: March 25-26, 2004
[Venue]
Resort Golden Palm http://www.resortgp.com.cn/
Sanya, Hainan island, China
***Land's End - Hainan is so remote on the sea that ancient people,
while believing that earth is square, really thought it is where
the land ends***
http://www.regenttour.com/chinaplanner/hainan/
[Sponsoring Organizations]
Association for Natural Language Processing of Japan (ANLP), Tokyo
Association for Computational Linguistics (ACL), Philadelphia
Association for Computational Linguistics and Chinese Language
Processing (ACLCLP), Taipei
Korea NLP society, Seoul
Chinese Information Processing Society of China (CIPSC), Beijing
(more to be added)
************************************************************************
This issue contains
[1] Conference Registration
[2] List of accepted papers
[3] Call for Papers: IJCNLP-04 Interactive Poster/Demo Sessions
Paper submission deadline: January 15, 2003
[4] Workshop on Named Entity Recognition for NLP Applications
Paper submission deadline: January 16, 2003 *** Extended ***
************************************************************************
[1] Conference Registration
The registration site for non-PRC participants is now open. Participants can register for the main conference (with tutorials and workshops) and/or the satellite symposium at http://www.rcl.cityu.edu.hk/ijcnlp04/registration.htm. Accommodation can also be booked simultaneously. PRC participants should register via the local organising committee (please refer to http://www.cipsc.org.cn/IJCNLP-04/). Enquiries on registration can be directed to ijcnlp04.enquiry@cityu.edu.hk.

Note to authors of accepted papers:
At least one author from each accepted paper should register for the conference by 24 January 2004 to avoid removal of the paper from the program. Each author can register for one paper only.
************************************************************************
[2] List of accepted papers
To Authors of accepted papers :If you found any errors in titles, names, etc., please let us know. (please send an e-mail to isahara@crl.go.jp)

[Oral Presentation]
A Three Level Cache-based Adaptive Chinese Language Model
Junlin Zhang, Weimin Qu, Le Sun, Lin Du, Yufang Sun
An Enhanced Semantic Indexing Implementation for Conceptual Information Retrieval
Eric Jiang
Information Flow Analysis with Chinese Text
Paulo Cheong, Dawei Song, Peter Bruza, Kam-Fai Wong
Chinese New Word Identification Based on Character Parsing Model
Yao Meng, Hao Yu, Fumihito Nishino
A Study of Semi-Discrete Matrix Decomposition for LSI in Automated Text Categorization
XiaoLong Wang, Yi Guan, Qiang Wang
Dit4Dah: Predictive Pruning For Morse Code Text Entry: Towards An Entry System For the Seriously Impaired
Kumiko Tanaka-Ishii, Ian Frank
Capturing Long Distance Dependency in Language Modeling: Am Empirical Study
Jianfeng Gao, Hisami Suzuki
Automatic Genre Detection of Web Documents
Chul Su Lim, Kong Joo Lee, Gil Chang Kim
Statistical Substring Reduction in Linear Time
Lv Xueqiang, Zhang Le
Improve Noun Phrase Coreference Resolution by Matching Strings
Xiaofeng Yang, Jian Su, Guodong Zhou, Chew Lim Tan
SVM-based Biological Named Entity Recognition using Minimum Edit-Distance Feature Boosted by Virtual Examples
Eunji Yi, Gary Geunbae Lee, Soo-Jun Park
Acquiring Bilingual Named Entity Translations from Content-aligned Corpora
Tadashi Kumano, Hideki Kashioka, Hideki Tanaka, Takahiro Fukusima
BBS Based Hot Topic Retrieval Using Back-Propagation Neural Network
Lan You, Jiayin Ge, Yongping Du, Xuanjing Huang, Lide Wu
High Speed Unknown Word Prediction Using Support Vector Machine For Chinese Text-to-Speech Systems
Juhong ha, Yu Zheng, Gary Geunbae Lee
You don't have to think twice if you carefully tokenize
Stefan Klatt
Semantic roles and the beauty of trees
Rik De Busser, Marie-Francine Moens
The Automatic Acquisition of Verb Subcategorisations and their Impact on the Performance of an HPSG Parser
Alex Chengyu Fang, John Carroll
Data-Oriented Parsing and the Penn Chinese Treebank
Mary Hearne, Andy Way
A Novel Pattern Learning Method for Open Domain Question Answering
Xuanjing Du, Xin Li Huang, Lide Wu, Yongping Du
FML-Based SCF Predefinition Learning for Chinese Verbs
Xiwu Han, Tiejun Zhao, Muyun Yang
Influence of Disambiguation on Cross-Language Information Retrieval
In-Su Kang, Seung-Hoon Na, Jong-Hyeok Lee
Natural Language Database Access using Semi-Automatically Constructed Translation Knowledge
In-Su Kang, Jae-Hak J. Bae, Jong-Hyeok Lee
Visual Semantics and Ontology of Eventive Verbs
Minhua Ma, Paul Mc Kevitt
Word Folding: Taking the Snapshot of Words Instead of the Whole
Jin-Dong Kim, Jun'ichi Tsujii
A Novel Approach to Improve Word Translations Extraction from Non Parallel, Comparable Corpora
Yun-Chuang Chiao, Jean-David Sta, Pierre Zweigenbaum
Automatic Learning of Parallel Dependency Treelet Pairs
Yuan Ding, Martha Palmer
Flexible Margin Selection for Reranking with Full Pairwise Samples
Libin Shen, Aravind K. Joshi
Discriminative Reranking for Machine Translation
Libin Shen, Anoop Sarkar, Franz Josef Och
Example-based Machine Translation without Saying Inferable Predicate
Eiji Aramaki, Sadao Kurohashi, Hideki Kashioka, Hideki Tanaka
Zero Pronoun Resolution based on Automatically Constructed Case Frames and Structural Preference of Antecedents
Daisuke Kawahara, Sadao Kurohashi
Chinese Chunk Identification Using SVMs plus Sigmoid
Yong-mei Tan, Tian-shun Yao, Qing Chen, Jing-bo Zhu
Corpus-oriented Grammar Development for Acquiring a Head-driven Phrase Structure Grammar from the Penn Treebank
Yusuke Miyao, Takashi Ninomiya, Jun'ichi Tsujii
Specification Retrieval -- How to Find Attribute-Value Information on the Web?
Minoru Yoshida, Hiroshi Nakagawa
Detection of Incorrect Case Assignments in Automatically Generated Paraphrases of Japanese Sentences
Atsushi Fujita, Kentaro Inui, Yuji Matsumoto
Acquiring Hyponymy Relations from Web Documents
Keiji Shinzato, Kentaro Torisawa
Improving Word Sense Disambiguation by Pseudo Samples
Wang Xiaojie, Yuji Matsumoto
Chinese Named Entity Recognition Based on Multilevel Linguistic Features
Honglei Guo, Jianmin Jiang, Gang Hu, Tong Zhang
Systematic Construction of Hierarchical Classifier in SVM-based Text Categorization
Yongwook Yoon, Changki Lee, Gary Geunbae Lee
Syntactic Analysis of Long Sentences based on S-clauses
Mi-Young Kim, Jong-Hyeok Lee
The Role of Semantic Information in Question Classification
Xin Li, Dan Roth, Kevin Small
Spoken versus Written Queries for Mobile Information Access: an Experiment with Mandarin Chinese
Heather Du, Fabio Crestani
Mining Biomedical Abstracts: What's in a Term?
Goran Nenadic, Irena Spasic, Sophia Ananiadou
Learning Cross-document Structural Relationships using Both Labeled and Unlabeled Data
Zhu Zhang, Dragomir Radev
Implementing the Syntax of Japanese Numeral Classifiers
Emily M. Bender, Melanie Siegel
Phoneme-based Transliteration of Foreign Names in Cross Language Information Retrieval
Wei Gao, Kam-Fai Wong, Wai Lam
Adding Syntax to Dynamic Programming for Aligning Comparable Texts
Dragomir R. Radev, Siwei Shen
Concept-based Sense Disambiguation for Korean Nouns
You-Jin Chung, Jong-Hyeok Lee
Categorizing Unknown Text Patterns for Information Extraction Using a Search Result Mining Approach
Chien-Chung Huang, Shui-Lung Chuang, Lee-Feng Chien
Causal Relation Extraction Using Cue Phrases and Lexical Pair Probabilities
Du-Seong Chang, Key-Sun Choi
Annotation of Gene Products in the Literature with Gene Ontology Terms using Syntactic Dependencies
Jung-jae Kim, Jong C. Park
The Use of SVM for Chinese New Word Identification
Hongqiao Li, Chang-Ning Huang, Jianfeng Gao
A re-examination of IR techniques in QA system
Yi Chang, Hongbo Xu, Shuo Bai
Window-based Method for Information Retrieval
Qianli Jin, Jun Zhao, Bo Xu
Bilingual Sentence Alignment Based on Punctuation Statistics and Lexicons
Thomas C. Chuang, Jian-Cheng Wu, Tracy Lin, Wen-Chie Shei, Jason S. Chang
Iterative CKY parsing for Probabilistic Context-Free Grammars
Yoshimasa Tsuruoka, Jun'ichi Tsujii
Feature Selection and Machine Learning for Pronominalization
Ji-Eun Roh, Jong-Hyeok Lee
Comparing Entropies within the Chinese language
Benjamin K Tsou, Tom B Y Lai, Ka-po Chow
Unsupervised Event Extraction from Biomedical Literature using Co-occurrence Information and Basic Patterns
Hong-woo Chun, Young-sook Hwang, Hae-chang Rim
Bilingual Chunk Alignment Based on Interactional Matching and Probabilistic Latent Semantic indexing
Feifan Liu, Qianli Jin, Jun Zhao, Bo Xu
An Example-based Study on Chinese Word Segmentation Using Critical Fragments
Qinan Hu, Haihua Pan, Chunyu Kit
Unsupervised Segmentation of Chinese Corpus using Accessor Variety
Haodi Feng, Kang Chen, Chunyu Kit, Xiaotie Deng
A Nearest-Neighbor Method for Resolving PP-Attachment Ambiguity
Shaojun Zhao, Dekang Lin
An Interactive Proofreading System for Inappropriately Selected Words on using Predictive Text Entry
Hideya Iwasaki, Kumiko Tanaka-Ishii
Acquiring Selectional Preferences in A Thai Lexical Database
Canasai Kruengkrai, Thatsanee Charoenporn, Virach Sornlertlamvanich, Hitoshi Isahara
Chinese Unknown Word Identification Using Class-based LM
Guohong Fu, Kang Kwong Luke
Practical Translation Pattern Acquisition from Combined Language Resouces
Mihoko Kitamura, Yuji Matsumoto
Harmonic Mean Weight through Hybrid Collaborative Filtering and Content based Filtering in Recommender System
Kyung-Yong Jung, Jung-Hyun Lee
------

[Poster Presentation]
Chinese Treebanks and Grammar Extraction
Keh-Jiann Chen, Yu-Ming Hsieh
Recognition of HTML Table Structure
Hidetaka Masuda, Shuichi Tsukamoto, Hiroshi Nakagawa
Improving Back-Transliteration by Combining Information Sources
Slaven Bilac, Hozumi Tanaka
Automatic Method of Extracting Foreign Words from Korean Corpora
Ok-Keum Kim, Tetsuya Ishikawa, Sang-Yool Lee, Jong-Hyeok Lee
Headword Percolation in a Multi-Parser Architecture for Natural Language Understanding
Helen Meng, Po-Chui Luk
Robust Speaker Identification System Based on Wavelet Transform and Gaussian Mixture Model
Wan-Chen Chen, Ching-Tang Hsieh, Eugene Lai
A Graph Grammar Approach to Map between Dependency Trees and Topological Models
Bernd Bohnet
Word-Spacing System with Statistics Extracted from the Processed Training Data
Mi-Young Kang, Sung-ja Choi, Hyuk-chul Kwon
Word Sense Disambiguation using Heterogeneous Language Resources
Kiyoaki Shirai, Takayuki Tamagaki
Improving PinYin to Chinese Conversion with a Whole Sentence Maximum Entropy Model
Zhang Le and Yao Tian-shun
Improving Quality of the Web Corpus
Youichi Sekiguchi, Kazuhide Yamamoto
Tagging Complex NEs with Maxent Models: Layered Structures versus Extended Tagset
Xiong Deyi, Yu Hongkui, Liu Qun
Deep Analysis of Modern Greek
Valia Kordoni, Julia Neu
Using a Smoothing Maximum Entropy Model for Chinese Nominal Entity Tagging
Jinying Chen, Nianwen Xue, Martha Palmer
Making Use of furigana
Gary Kacmarcik
Building a parallel bilingual syntactically annotated corpus
Martin Cmejrek, Jan Curin, Jiri Havelka, Vladislav Kubon
Processing Metonymic Expressions for the Matching of a QA System
Yoji Kiyota, Sadao Kurohashi, Fuyuko Kido
A Collaborative Ability Measurement for Co-Training
Dan Shen, Jie Zhang, Jian Su, Guodong Zhou, Chew-Lim Tan
Using a Paraphraser to Improve Machine Translation Evaluation
Andrew Finch, Yasuhiro Akiba, Eiichiro Sumita
Deterministic dependency structure analyzer for Chinese
Yuchang Cheng, Masayuki Asahara, Yuji Matsumoto
A Comparative Study on the Use of Labeled and Unlabeled for Large Margin Classifiers
Hiroya Takamura, Manabu Okumura
Detecting sentence boundaries in Japanese speech transcriptions using a morphological analyzer
Sachie Tajima, Hidetsugu Nanba, Manabu Okumura
Improving Relevance Feedback in the Language Modeling Approach: Maximum a Posteriori Probability Criterion and Three-component Mix-ture Model
Seung-Hoon Na, In-Su Kang, Jong-Hyeok Lee
A Persistent Feature-Object Database for Intelligent Text Archive Systems
Takashi Ninomiya, Jun'ichi Tsujii, Yusuke Miyao
A English-Hindi Statistical Machine Translation System
Raghavendra Udupa, Tanveer A Faruquie
Fast Reinforcement Learning of Dialogue Policies using Linear Function Approximation
Matthias Denecke, Kohji Dohsaka, Mikio Nakano
Collecting Evaluative Expressions for Opinion Extraction
Nozomi Kobayashi, Kentaro Inui, Yuji Matsumoto, Kenji Tateishi, Toshikazu Fukushima
Mining Table Information on the Internet
Sung-won Jung, Hyuk-chul Kwon
Learning to Filter Junk E-Mail from Positive and Unlabeled Examples
Karl-Michael Schneider
The Hinoki Treebank A Treebank for Text Understanding
Francis Bond, Sanae Fujita, Chikara Hashimoto, Kaname Kasahara,
Shigeko Nariyama, Eric Nichols, Akira Ohtani, Takaaki Tanaka, Shigeaki Amano
Selecting Prosody Parameters for Unit Selection Based Chinese TTS
Minghui Dong, Kim-Teng Lua
Parsing Mixed Constructions in a Type Feature Structure Grammar
Jong-Bok Kim, Jaehyung Yang
How Effective is Query Expansion for Finding Novel Information?
Min Zhang, Shaoping Ma
N-fold Templated Piped Correction
Dekai Wu, Grace Ngai, Marine Carpuat
User Adaptation in MT-mediated Communication
Kentaro Ogura, Yoshihiro Hayashi, Saeko Nomura, Toru Ishida
************************************************************************
[3] Call for Papers: IJCNLP-04 Interactive Poster/Demo Sessions
You may have a very cool demo but don't have time to package a full size of paper for main conference, or you get a late breaking report but has not yet finished solid evaluation, or you prefer to present your works in an interactive style, this session will provide you an exciting channel to show your cool demos and ideas and get valuable feedbacks at the same time.

The special session for interactive posters and demonstrations provided in IJCNLP-04 will welcome poster/demo presentations with novel ideas and profound applications, or the works that are best presented and discussed in an interactive style. This session will provide a forum of academic and technical exchanges. Presentations from both the academic and industries are welcomed. The topics of interest will cover the same area of the main conference (http://www-tsujii.is.s.u-tokyo.ac.jp/ijc-nlp04/submission.html).

The authors should submit an original paper (no more than 4 pages in IJCNLP format) that describes the problem of the research and the novel methods. Presentations with demos should include an outline of the system design and enough details to allow the evaluation of
technical solidness and usefulness. The equipments required for the demonstration must be provided. The Interactive Poster/Demo papers will be included in a separated proceeding that is in parallel to the main conference proceedings. Each submission will be blind reviewed by three reviewers. Reviewing will be managed by an international program committee.

Presentation Style of the Interactive Poster/Demo Sessions
The Interactive Poster/Demo Sessions will run in the afternoons of March 22 and March 23. Each presentation will receive a booth with a 1.8m x 0.6m desk and a 1.8m x 2.1m panel. Network connection and electricity outlets will be supplied to each booth.

Submission Information
Submissions should follow the format of IJCNLP proceedings and should not exceed four (4) pages, including references. Since the reviewing will be blind, the paper should not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity should be avoided.

Submission Procedure
All papers must be submitted electronically via email to the following address. Either a PDF or PS file must be sent as an attached file. Please use the first author's surname to name the file. The Subject field should be "IJCNLP-04 Poster/Demo submission". Please include the name, affiliation and email address of the contact person in the body of your email.

The Important Dates
Paper submission deadline: January 15, 2003
Notification of acceptance: Feb. 15, 2004
Camera ready papers due: Feb 28, 2004
Please submit papers to: mingzhou@microsoft.com

Program Committee for Interactive Poster/Demo sessions
Chair: Ming Zhou, Microsoft Research Asia

PC members:
Masaaki Nagata, NTT
Takenobu Tokunaga, Tokyo Institute of Technology
Genichiro Kikui, ATR
Sadao Kurohashi, The University of Tokyo
Donghong Ji, Kent Ridge Digital Labs
Jian-Yun Nie, Univ. of Montreal
Dekang Lin, Univ. of Alberta
Hsin-Hsi Chen, National Taiwan University
Lee-Feng Chien, Academia Sinica
Kam-Fai Wong, Chinese University of Hong Kong
Gary Geunbae Lee, POSTECH
Jong-Hyeok Lee, POSTECH
Maosong Sun, Tsinghua University
Jun Zhao, Institute of Automation, Chinese Academy of Sciences
Tiejun Zhao, Harbin Institute of Technology
Qun Liu, China Academy of Science
Haifeng Wang, Toshiba R&D Centre
Kui-Lam Kwok, City University of New York
Dan Moldovan, University of Texas at Dallas
Chin-Yew Lin, ISI/USC
Tilman Becker, DFKI
Rens Bod, University of Amsterdam
Harry Bunt, Tilburg University
Christian Boitet, Universite Joseph Fourier
Michael Zock, LIMSI
************************************************************************
[4] Workshop on Named Entity Recognition for NLP Applications
*** SUBMISSION DEADLINE NOW EXTENDED TO 16 JANUARY 2004 ***
Workshop website: http://personal.cityu.edu.hk/~rlolivia/W4_NE.htm

Named Entities (NEs) occupy a considerable proportion in natural language and have remained an important area in natural language processing (NLP). The recognition of proper names as unknown words has long been an issue in word segmentation and part-of-speech tagging, especially for non-alphabetic Asian languages and interlingual NLP involving these languages. Named entities constitute significant pieces of data in information extraction. Proper transliteration of named entities, especially proper names, is critical for the intelligibility and accuracy of machine translation output.This workshop aims at bringing researchers
together to discuss the issues and advances in NE recognition and extraction, and how NE could be handled most cost-effectively in a variety of NLP applications.

Papers are invited for original and unpublished research on all aspects of NE recognition and extraction, including but not limited to:
- Symbolic and statistical models for NE recognition
- NE recognition systems
- Translation of NEs across multiple languages
- Resources (lexicons, grammars) for NE extraction
- NE recognition as a subtask in NLP applications
- Evaluation of NE processing in NLP applications

Submission Method
Papers should be written in English and may not exceed 7 pages (including references, and using 11pt or 12pt for the main text). Simultaneous submission to other conferences or workshops must be clearly indicated on the identification page (see below).

Nevertheless, a paper accepted for presentation in this workshop cannot be presented or have been presented in any other meeting with publicly published available proceedings.

We strongly recommend the use of the LaTeX style files or MS-Word document template for IJCNLP-04. These style files can be downloaded from
http://www-tsujii.is.s.u-tokyo.ac.jp/ijc-nlp04/submission.html.

As reviewing will be blind, self-references that reveal the author's identity (e.g., "We previously showed (Smith, 1991) .") should be avoided in the submission. Instead, use references like "Smith previously showed (Smith, 1991) .". Please include, on a separate identification page, the following information: title, name(s) of author(s), affiliation(s), email address(es), up to 5 keywords, whether the paper is under consideration for other conferences, and a short summary of the paper.

Please submit your paper electronically to rlolivia@cityu.edu.hk by 16 January 2004. Acceptable file formats are Portable Document Format (.pdf), PostScript (.ps), and MS Word (.doc), with all non-ASCII fonts embedded.

Important Dates
Submission Deadline: 16 January 2004 *** Extended ***
Notification of Acceptance: 31 January 2004
Camera-Ready Paper Due: 10 February 2004
Workshop Date: 26 March 2004

Program Committee for Workshop on Named Entity Recognition for NLP Applications
Chair: Benjamin Tsou (City University of Hong Kong)

PC members:
Roberto Basili (University of Rome Tor Vergata, Rome)
Ralph Grishman (New York University, New York)
Kevin Humphreys (Microsoft, Redmond)
Hideki Isozaki (NTT Communication Science Labs, Kyoto)
Gary Geunbae Lee (POSTECH, Pohang)
Masaaki Nagata (NTT Cyber Space Laboratories, Kanagawa)
Hwee Tou Ng (National University of Singapore, Singapore)
Thierry Poibeau (Institut National des Langues et Civilisations
Orientales, Paris)
Manabu Sassano (Fujitsu Laboratories Ltd., Kawasaki)
Satoshi Sekine (New York University, New York)
Rou Song (Beijing Language and Culture University, Beijing)
Kiyotaka Uchimoto (Communications Research Laboratory, Kyoto)
Takehito Utsuro (Kyoto University, Kyoto)
Jingbo Zhu (Northeastern University, Shenyang)
************************************************************************