Semiautomatic Acquisition of Machine
Translation Knowledge from Examples

Fuji REN
Institute of Information science ,
Hiroshima City University,
341, OzukaHigasi,AsaMinamiKu,Hiroshima,
73131, Japan
ren@its.hiroshimacu.ac.jp
Lixin Fan
Digital Express Corporation
3601, OzukaNisi 614, AsaMinamiKu, Hiroshima,
73131, Japan
JianYun NIE
DIRO, Universit de Montral
C.P. 6128, succ. centrevile, Qubec,
H3C 3J7 Canada
nie@iro.umontreal.ca
Youliang JIAN
Computer Institute,
Dalian University of Technology
116023, Dalian, China
newyou@dlut.edu.cn

Abstract
A crucial problem in rulebased machine translation is the acquisition of translation knowledge. Many
studies have been conducted for automatic acquisition in the past, but they require a great deal of
annotated examples. In this paper, we describe a semiautomatic acquisition from translation examples in
JapaneseChinese environment. Whenever necessary, the process interacts with a user (a linguist) who
will provides additional information and constraints for generalizing the translation examples. The semi-automatic 
approach is more efficient in the sense that less examples are required than automatic
approaches. Once the acquired knowledge is integrated with an MT system, we observe an improvement
in translation quality.

References
Dagan, I., Church, K. (1997) Termight: Coordinating humans and machine in bilingual terminology
acquisition, Machine Translation, 12/12, pp. 89107.
Fung, P., McKeown, K. (1997) A technical word and termtranslation aid using noisy parallel corpora
across language groups, Machine Translation, 12/12, pp. 5387.
Furuse, O. and Iida, H. (1992) An Examplebased Method for TransferDriven Machine Translation,
Proc. TMI92, pp. 139150.
Jian Y., Chang H., Wang X., Huang D. (1997) A Japanese parser using dependence relation, Language
Engineering, pp. 258265.
Kaji, H., Kida, Y. and Morimoto, Y. (1992) Learning Translation Templates from Bilingual Text, Proc.
COLING92, pp. 672678.
Kay, M. (1997) The proper place of men and machine in language translation, Machine Translation,
12/12, pp. 323.
Kitamura, M. and Matsumoto, Y. (1996) Automatic Acquisition of Translation Rules from Parallel
Corpora, Transactions of IPSJ, 37 / 6, pp. 10301040.
Lang, J.M., Gaussier, ., Daille, B. (1997) Bricks and skeletons: Some ideas for the near future of
MAHT, Machine Translation, 12/12, pp. 3951.
Ren F. (1996), SWKJC Machine Translation System Based on Translation Rules Acquired from
Corpora, Technique Report of Hiroshima City University,Technique Report of Hiroshima City
University,HCUIS96004, pp.131.
Sato, S. (1995) MBT2: A Method for Combining Fragments of Examples in Examplebased Translation,
Artificial Intelligence, 75, pp. 3149.
Sun, M. (1994) Chinese syntactic analysis using a multiple pass, deterministic algorithm and its
application in text understanding, Proceedings of Processing of Linguistic Information, pp. 103168
Watanabe, H. (1993) A Method for Extracting Translation Patterns from Translation Examples, Proc.
TMI93, pp. 292301.
Yu, S. (1995) A hypothesis about restricted regular Chinese, Proceedings of Chinese modernization, pp.
193205
Zajac, R., Vanni, M. (1997) Glossarybased MT engines in a multilingual analyst's workstation
architecture, Machine Translation, 12/12, pp. 131151.

