NTCIR Workshop 1
 


Proceedings of the First NTCIR Workshop
on Research in Japanese Text Retrieval
and Term Recognition

August 30 - September 1, 1999
KKR Hotel Tokyo, Tokyo, Japan

Copyright (C) 1999 National Center for Science Information Systems
ISBN: 4-924600-77-6

Organized by:
    NACSIS  (National Center for Science Information Systems)
In cooperation with:
    IPSJ  (Information Processing Society of Japan)
    SIG-FI (Fundamental Infology), IPSJ
Supported by:
    JSPS (Japan Society for the Promotion of Science) "Research for the Future Program: Studies on Ubiquitous Information Systems for Utilization of Highly Distributed Information Resources" (Principal Investigator: Jun Adachi, Professor, NACSIS)


Preface
Noriko Kando (NACSIS)


1. Keynote Speech

"The Text REtrieval Conference (TREC)"
Donna Harman (National Institute of Standards and Technology) ¡¡


2. IR Tasks (Ad Hoc IR Task and Crosslingual IR Task)

2.1 Overview & Advisory Report

"Overview of IR tasks"
Noriko Kando, Kazuko Kuriyama, Toshihiko Nozue, Koji Eguchi, Hiroyuki Kato and Soichiro Hidaka (NACSIS)   "NTCIR Advisor Report"
Yasushi Ogawa (Software Research Center, RICOH Co., Ltd.)


2.2 Research Articles

---- Ad Hoc IR and Cross-lingual ----

"Comparing Multiple Methods for Japanese and Japanese-English Text Retrieval"
Aitao Chen*, Fredric C. Gey**, Kazuaki Kishida***, Hailing Jiang* and Qun Liang* (*School of Information Management and Systems, University of California at Berkeley, **UC Data Archive & Technical Assistance (UC DATA), ***Faculty of Cultural Information Resources, Surugadai University)

"Information Retrieval Based on Stochastic Models"
Masaki Murata, Kiyotaka Uchimoto, Hiromi Ozaku and Hitoshi Isahara (Communications Research Laboratory, Ministry of Posts and Telecommunications)

"NTCIR Experiments at Matsushita: Ad-hoc and CLIR Task"
Mitsuhiro Sato, Hayashi Ito and Naohiko Noguchi (Multimedia Systems Research Laboratory, Matsushita Electric Industrial Co., Ltd.)

 ---- Ad Hoc IR ---- "R2D2at NTCIR: Using the Relevance-based Superimposition Model"
Teruhito Kanazawa (Graduate School of Engineering, University of Tokyo)

"Japanese Word Segmentation Using Similarity Measure for IR"
Tomohiro Ozawa*, Mikio Yamamoto*, Kyoji Umemura** and Kenneth W. Church*** (*University of Tsukuba, **Toyohashi University of Technology, ***AT&T Labs - Research)

"Experiments with Japanese Text Retrieval Using mg"
Phil Vines*, Ross Wilkinson** (*Department of Computer Science, RMIT, **CSIRO)

¡¡

 ---- Ad Hoc IR using NLP Techniques ----
  "Notes on Phrasal Indexing: JSCB Evaluation Experiments at NTCIR AD HOC"
Sumio Fujita (JUSTSYSTEM Corporation)

"Proposal and Evaluation of Significant Words Selection Method Based on AIC"
Shigeki Ohira and Katsuhiko Shirai (School of Science and Engineering, Waseda University)

"Structured Index System at NTCIR1: Information Retrieval using Dependency Relationship between Words"
Atsushi Matsumura, Atsuhiro Takasu and Jun Adachi (NACSIS)

 ---- Interactive Ad Hoc Retrieval ---- "Interactive Document Search with DualNAVI"
Yoshiki Niwa, Makoto Iwayama, Toru Hisamitsu, Shingo Nishioka, Akihiko Takano, Hirofumi Sakurai and Osamu Imaichi (Central Research Laboratory, Hitachi, Ltd.) ---- Cross-Lingual IR ---- "Dynamic Programming: A New Paradigm for Information Retrieval"
Ryuichi Sawada and Kyoji Umemura (Toyohashi University of Technology)

"Cross-Language Information Retrieval for NTCIR at Toshiba"
Tetsuya Sakai, Yasuyo Shibazaki, Masaru Suzuki, Masahiro Kajiura, Toshihiko Manabe and Kazuo Sumita (Toshiba R&D Center)

"Description of the NTU Japanese-English Cross-Lingual Information Retrieval System Used for NTCIR Workshop"
Chuan-Jie Lin, Wen-Cheng Lin, Guo-Wei Bian and Hsin-Hsi Chen (Department of Computer Science and Information Engineering, National Taiwan University)

"Cross Language Information Retrieval Based on Comparable Corpora"
Satoshi Nakazawa*, Takayoshi Ochiai**, Kenji Satoh* and Akitoshi Okumura*
(*C&C Media Research Laboratories, NEC Corporation, **Open Technology System Division, NEC Information Systems, Ltd.)

"NTCIR CLIR Experiments at the University of Maryland"
Douglas W. Oard and Jianqiang Wang (Digital Library Research Group, College of Library and Information Services, University of Maryland)

"Cross-Language Information Retrieval at ULIS"
Atsushi Fujii and Tetsuya Ishikawa (University of Library and Information Science)

 ---- IR with Heterogenous Documents ---- "Multi-lingual Multi-media Information Retrieval System"
Shoji Mizobuchi*, Sankon Lee*, Fumihiko Kawano*, Tsuyoshi Kobayashi*, Takahiro Komatsu*, Jun-ichi Aoe** (*Graduate School of Engineering, University of Tokushima, **Department of Information Science & Intelligent Systems, University of Tokushima) ---- Without Oral Presentation ---- "A Character-based Indexing and Word-based Ranking Method for Japanese Text Retrieval"
Toshikazu Fukushima and Susumu Akamine (Human Media Research Laboratories, NEC Corporation)

"Development of a Related Document Retrieval System and Evaluation of the System Using NTCIR-1"
Hiroshi Umemoto, Tsutomu Kuramochi, Yasuhiro Ishitobi and Masakazu Tateno (Fuji Xerox Co., Ltd.)

"Idea-deriving Information Retrieval System"
Tsuneaki Kato*, Shigeo Shimada**, Mutsumi Kumamoto** and Kazumitsu Matsuzawa*** (*NTT Communication Science Laboratories, **NTT Advanced Tech. Corp, ***NTT Service Integration Laboratories)

¡ÈAn Advanced System for Information Retrieval via Key Concepts¡É
Hiroyuki Kameda, Noriko Oomori, Chiaki Kubomura and Yukinobu Tanifuji (School of Information Technology, Faculty of Engineering, Tokyo University of Technology)

 2.3 Evaluation Results of Each Run Ad Hoc IR Task

Crosslingual IR Task

Monolingual IR Task

 2.4 System Description Form of Each Group Ad Hoc IR Task     complete description

Crosslingual IR Task      complete description

 3. TMREC Task (Automatic Term Recognition and Role Analysis Task)

3.1 Overview and Evaluation

"Overview of TMREC Tasks"
Kyo Kageura*, Masaharu Yoshioka*, Koichi Takeuchi*, Teruo Koyama*, Keita Tsuji**, Fuyuki Yoshikane** and Maho Okada* (*NACSIS, **Graduate School of Education, University of Tokyo)

"Evaluation of the Term Recognition Task"
Kyo Kageura*, Masaharu Yoshioka*, Keita Tsuji**, Fuyuki Yoshikane**, Koichi Takeuchi* and Teruo Koyama* (*NACSIS, **Graduate School of Education, University of Tokyo)

"Evaluation of the Keyword Extraction Task"
Koichi Takeuchi, Masaharu Yoshioka, Teruo Koyama and Kyo Kageura (NACSIS)

"Evaluation of the Role Analysis Task"
Teruo Koyama, Masaharu Yoshioka, Koichi Takeuchi and Kyo Kageura (NACSIS)

 3.2 Research Articles "Term Recognition by Using Different Field Corpora"
Kiyotaka Uchimoto*, Satoshi Sekine**, Masaki Murata*, Hiromi Ozaku* and Hitoshi Isahara* (*Communications Research Laboratory, Ministry of Posts and Telecommunications, **New York University)

"Compound Noun Based System for Automatic Term Recognition Task"
Hiroshi Nakagawa (Information Technology Center, The University of Tokyo)

"Extraction of Semantic Relationships among Terms to Construct Organized Knowledge Resources"
Takayuki Morimoto*, Tetsuya Maeshiro**, Yuzuru Fujiwara* (* Department of Information Science, Kanagawa University, ** ATR Human Information Processing Research Laboratories)

"NTCIR Experiments at Matsushita: TMREC Task"
Yoshio Fukushige and Naohiko Noguchi (Multimedia Systems Research Laboratory, Matsushita Electric Industrial Co., Ltd.)

"Term Extraction Using A New Measure of Term Representativeness"
Toru Hisamitsu, Yoshiki Niwa, Shingo Nishioka, Hirofumi Sakurai, Osamu Imaichi, Makoto Iwayama and Akihiko Takano (Central Research Laboratory, Hitachi, Ltd.)