Machine Translation Summit VII ’99

“MT in the Great Translation Era”


September 13-17, 1999

Kent Ridge Digital Labs, Singapore





                                What should we do next for MT system development? – Hozumi Tanaka ..... 3



                                Chart translation – Martin Kay ..... 9

                                What can MT do for multilingualism on the Net? – Toru Nishigaki .... 15

                                SAIL: present and future – Jo Lernout .... 21



                                Retrospect and prospect in computer-based translation – John Hutchins .... 30



                Session S1: Controlled language

                                Controlled languages for machine translation: state of the art – Hiroyuki Kaji .... 37

                                Controlled language – issues in checkers’ design – Uus Knops .... 40

                                Controlled language for multilingual machine translation – Teruko Mitamura .... 46

                Session S2: Localization

                                Translation technology applications for the localization industry – Michael Anobile .... 55

                                MT and TM technologies in localization industry: the challenge of integration – Nikolai Puntikov .... 63

                Session S3: Survey reports on MT in each area

                                Regional survey: M(A)T in North America – Elliott Macklovitch .... 73

                                Computer assisted translation system – an Indian perspective – Hemant Darbari .... 80

                                The research and development of machine translation in China – Aiping Fu .... 86

                                Report on machine translation market in Japan – Yoshiyuki Sakamoto and Minoru Moriguchi .... 92

                                Machine translation in Korea – Se-Young Park and Gil-Rok Oh .... 100

Session S4: MT and speech

                                Prospects for advanced speech translation – Hitoshi Iida .... 107

                                Robust spoken translation at ITC-IRST – Gianni Lazzari .... 114

                                Translation systems under the C-STAR framework [abstract only]– Alex Waibel .... 121

                Session S5: MT from the research perspective

A research perspective on how to democratize machine translation and translation aids aiming at high quality final output – Christian Boitet .... 125

From parallel grammar development towards machine translation – a project overview – Anette Frank .... 134

                                MT from the research perspective – Yussoff Zaharin .... 143

                Session S6: Views from users

                                FAMT is alive and well – Marjorie Leσn .... 149

                Session S7: Multilingual information access

                                Applications using multilinguality: IR, summarization and generalization – Vilas Wuwongse .... 155

A scalable cross-language metasearch architecture for multilingual information access on the Web – Yoshihiko Hayashi, Genichiro Kikui and Toshiaki Iwadera .... 157

Complementing dictionary-based query translations with corpus statistics for cross-language IR – Sung Hyon Myaeng and Mung-Gil Jang .... 165

                Session S8: MT for the next century

                                Machine translation for the next century  – Jun-ichi Tsujii .... 175

                                Otelo and the Domino translation object – Alan Barrett .... 177

Sharing dictionaries among MT users by common formats and social filtering framework – Shin-ichiro Kamei .... 180

                                A customizable, self-learning parameterized MT system: the next generation – Keh-Yih Su and Jing-Shin Chang .... 182



            Session PN1: International cooperation – from funding agencies’ point of view

Human language technologies for the information society: roles, plans and visions of funding agencies – Antonio Sanfilippo, Shuo Bai, Roberto Cencioni, Akira Izumi, Gary Strong and Dimitrios Theologitis .... 191

            Session PN2: MT evaluation

MT evaluation – Margaret King, Eduard Hovy, Benjamin K. T’sou, John White and Yusoff Zaharin .... 197



            Session G1: MT methodologies

Applying TDMT to abstracts on science and technology – Hideki Kashioka, Hiroko Ohta, Yoshiko Shirokizawa and Kazutaka Takao .... 213

UNL-French deconversion as transfer & generation from an interlingua with possible quality enhancement through offline human interaction – Gilles Sιrasset and Christian Boitet .... 220

Solutions to problems inherent in spoken-language translation: the ATR-MATRIX approach – Eiichiro Sumita, Setsuo Yamada, Kazuhide Yamamoto, Michael Paul, Hideki Kashioka, Kai Ishikawa and Satoshi Shirai ... 229

            Session G2: Example-based MT

Portuguese-Chinese machine translation in Macao – Yi-Pmg Li, Chi-Man Pun and Fei Wu .... 236

Example-based machine translation based on the synchronous SSTC annotation schema – Mosleh H. Al-Adhaileh and Tang Enya Kong.... 244

Inducing translation templates for example-based machine translation – Michael Carl ....                  250

Session G3 :   Multilingual human language technology

Development of an intranet MT system adapting to usage domain – Nobutoshi Hatanaka ... 259

The next step: moving to an integrated MT system for high-volume environments – Walter K. Hartmann ...  266

TransRouter : a decision support tool for translation managers – Margaret King .... 272

Deploying the SAE J2450 translation quality metric in MT projects – Jφrg Schόtz ... 278

Session G4 :   MT evaluation

Evaluation experiment  for reading comprehension of machine translation outputs – Masaru Fuji .... 285

Study on evaluation of WWW MT systems – Shinichiro Miyazawa, Shoichi Yokoyama, Masaki Matsudaira, Akira Kumano, Shuji Kodama, Hideki Kashioka, Yoshiko Shirokizawa and Yasuo Nakajima ....290

A new evaluation method for speech translation systems and a case study on ATR-MATRIX from Japanese to English – Toshiyuki Takezawa, Fumiaki Sugaya, Akio Yokoo and Seiichi Yamamoto   • • •  299

Session G5 :   Multilingual information processing

Machine translation for information access across the language barrier : the MuST system – Chin-Yew Lin .... 308

Multilingual document language recognition for creating corpora – Yevgeny Ludovik and Ron Zacharski .... 317

Session G6 :   Translation tools

Interactive MT as support for non-native language authoring – Svetlana Sheremetyeva and Sergei Nirenburg .... 324

Formalizing translation memories – Emmanuel Planas and Osamu Furuse .... 331

The PARS family of MT systems : a 15-year love story – Michael S. Blekhman, Olga Bezhanova, Andrei Kursin and Alia Rakova .... 340

Session G7 :   Language resources

Parallel text collections at Linguistic Data Consortium – Xiaoyi Ma .... 346

The ELAN Slovene-English aligned corpus – Tomaz Erjavec ... 349

Harmonised large-scale syntactic/semantic lexicons: a European multilingual infrastructure – Nicoletta Calzolari and Antonio Zampolli .... 358

Developing knowledge bases for MT with linguistically motivated quality-based learning – Evelyne Viegas .... 366

Session G8 :   System presentation (1)

A pipelined multi-engine approach to Chinese-to-Korean machine translation: MATES/CK – Min Zhang and Key-Sun Choi .... 375

Machine translation system PENSΙE: system design and implementation – Sayori Shimohata, Toshiki Murata, Atsushi Ikeno, Tsuyoshi Fukui and Hideki Yamamoto. .... 380

Rapid development of translation tools – Jan Amtrup, Karine Megerdoomian and Remi Zajac .... 385

Session G9 :   Knowledge extraction

The use of abstracted knowledge from an automatically sense-tagged corpus for lexical transfer ambiguity resolution – Hui-Feng Li, Namwon Heo. Kyounghi Moon and Jong-Hyeok Lee .... 390

Towards the automatic acquisition of lexical selection rules – Jin Yang .... 397

A bootstrap approach to automatically generating lexical transfer rules – Davide Turcato, Paul McFetridge, Fred Popowich and Janine Toole .... 404

Session Gl0 :   Statistical methods

Target word selection with co-occurrence and translation information – Su Jian, Guo Jin and Tong Loong Cheong .... 412

Using a target language model for domain independent lexical disambiguation – Jim Cowie, Yevgeny Ludovik and Sergei Nirenburg .... 417

Article selection using probabilistic sense disambiguation – Hian-Beng Lee .... 421

Compound noun decomposition using a Markov model – Jongwoo Lee, Byoung-Tak Zhang and Yung Taek Kim .... 427

Session G1l :   System presentation (2)

English-to-Korean Web translator : “FromTo/Web-EK” – Sung-Kwon Choi, Taewan Kim, Sanghwa Yuh, Han-Min Jung, Chul-Min Sim and Sang-Kyu Park .... 432

ALTFLASH: a Japanese-to-English machine translation system for market flash reports – Hajime Uchino, Yoshifumi Ooyama and Osamu Furuse .... 438

ALT-J/M a prototype Japanese-to-Malay translation system – Kentaro Ogura, Francis Bond and Yoshifumi Ooyama .... 444

Session G12 :   Asian language processing

An automated mandarin document revision system using both phonetic and radical approaches – June-Jei Kuo .... 449

The pitfalls and complexities of Chinese to Chinese conversion – Jack Halpern and Jouni Kerman .... 458



Session PS1 :   Poster session (1)

From To K/E: a Korean-English machine translation system based on idiom recognition and fail softening – Byong-Rae Ryu, Youngkil Kim, Sanghwa Yuh and Sangkyu Park .... 469

Transfer-based Japanese-Chinese translation implemented on an e-mail system – Junichi Matsuda and Hiroyuki Kumai .... 476

A Cantonese-English machine translation system PolyU-MT-99 – Yan Wu and James Liu .... 481

WEBTRAN: a controlled language machine translation system for building multilingual services on Internet – Aarno Lehtola, Jarno Tenni, Catherine Bounsaythip and Kristiina Jaaranen .... 487

Improvement of translation quality of English newspaper headlines by automatic preediting – Takehiko Yoshimi and Ichiko Sata .... 496

Transfer in experience-guided machine translation -- Gang Zhao and Junichi Tsujii .... 501

Example-based machine translation of part-of-speech tagged sentences by recursive    division – Tantely Andriamanankasina, Kenji Araki and Koji Tochinai .... 509

A new way to conceptual meaning representation – Xiaojie Wang and Yixin Zhong .... 518

Using computational semantics for Chinese translations – Evelyne Viegas, Wanying Jin and Stephen Beale .... 522

Session PS2 :   Poster session (2)

Sources of linguistic knowledge for minority languages -- Harold L. Somers .... 531

BITS: a method for bilingual text search over the Web – Xiaoyi Ma and Mark Y. Liberman .... 538

Sharing syntactic structures – Masahiro Ueki, Takenobu Tokunaga and Hozumi Tanaka .... 543

A deterministic dependency parser for Japanese -- Ulrich Germann .... 547

A new approach to the translating telephone   – Robert Frederking, Christopher Hogan and Alexander Rudnicky .... 556

A method of evaluation of the quality of translated text – Satoshi Yamauchi .... 564

Quantitative evaluation of machine translation using two-way MT – Shoichi Yokoyama, Akira Kumano, Masaki Matsudaira, Yoshiko Shirokizawa, Mutsumi Kawagoe, Shuji Kodama, Hideki Kashioka, Terumasa Ehara. Shinichiro Miyazawa and Yasuo Nakajima .... 568

Task-based evaluation for machine translation -- Jennifer B. Doyon, Kathryn B. Taylor and John S. White ... 574

Experiment report of a commercial machine translation in a manufacturing industry domain – Orie Fukutomi .... 579

Session PS3 :   Poster session (3)

Collection of dictionary data through Internet translation service – Keisuke Nakayama and Akira Kumano .... 586

Term Builder: a lexical knowledge acquisition tool for the Logos machine translation system – Brigitte Orliac and Kutz Arrieta .... 593

Computer-aided translation tools for Russian. Ukrainian, and English – Michael S. Blekhman, Maryna Byezhanova, Andrei Kursin, Igor Backlan, Alexander Kazakov and Vladimir Petrov .... 598

Translation camera -- Yasuhiko Watanabe, Yoshihiro Okada, Yeun-Bae Kim and Tetsuya Takeda .... 601

A new diagnostic system for J-E translation ILTS by global matching algorithm and POST parser – Liang Chen and Naoyuki Tokuda .... 608

Linking translation memories with example-based machine translation -- Michael Carl and Silvia Hansen .... 617

Towards an interlingual treatment of modality -- Christoph Neumann .... 625

Resolving category ambiguity of non-text symbols in Mandarin text – Feng-Long Hwang and Ming-Shing Yu .... 633

Automatic domain recognition for machine translation .... Elke D. Lange and Jin Yang .... 641

A multilevel framework for incremental development of MT systems – Remi Zajac .... 646