Sync/Trans: Simultaneous Machine Interpretation between English and Japanese
This paper describes Sync/Trans, an incremental spoken language translation system. The system has been being developed for efficiently translating a spontaneous speech dialogue between an English speaker and a Japanese speaker. Its purpose being to behave as a simultaneous interpreter, the system produces the target output synchronously with the source input. Sync/Trans has the following features: (1) the system consists of modules that work in a synchronous fashion, (2) the system translates the source language possibly word-by-word according to the appearance order, (3) the system utilizes grammatically ill-formed expressions for the speech output, and (4) the system corrects the grammatical ill-formed expressions for the speech input at a pretty early stage. An experimental system for translating English speech into Japanese speech has been implemented. A few experimental results have shown Sync/Trans to be a promising system for simultaneous interpretation.
KeywordsMachine Translation Translation Result Source Language English Sentence Transfer Rule
Unable to display preview. Download preview PDF.
- 1.Amtrup J.W.: Chart-based Incremental Transfer in Machine Translation, Proceedings of the 6th International Conference of Theoretical and Methodological Issues in Machine Translation, pp. 188–195 (1995).Google Scholar
- 2.Furuse, O. and Iida, H.: Incremental Translation Utilizing Constituent Boundary-Patterns, Proceedings of the 16th International Conference on Computational Linguistics, pp. 412–417 (1996).Google Scholar
- 3.Iida, H., and Sumita, E. and Furuse, O.: Spoken-Language Translation Method Using Examples, Proceedings of the 16th International Conference on Computational Linguistics, pp. 1074–1077 (1996).Google Scholar
- 4.Inagaki Y. and Matsubara S.: Models for Incremental Interpretation of Natural Language, Proceedings of the 2nd Symposium on Natural Language Processing, pp. 51–60 (1995).Google Scholar
- 5.Kay M.: Algorithm Schemata and Data Structures in Syntactic Processing, Technical Report CSL-80-12, Xerox PARC (1980).Google Scholar
- 6.Kitano, H.: Incremental Sentence Production with a Parallel Marker-Passing Algorithm, Proceedings of the 13th International Conference on Computational Linguistics, pp. 217–222 (1990).Google Scholar
- 7.Kitano, H.: Speech-to-Speech Translation: A Massively Parallel Memory-based Approach, Kluwer Academic Publishers (1993).Google Scholar
- 8.Matsubara S. and Inagaki Y.: Utilizing Extra-Grammatical Phenomena in Incremental English-Japanese Machine Translation, Proceedings of the 7th International Conference on Theoretical and Methodological Issues in Machine Translation, pp. 138–145 (1997).Google Scholar
- 9.Matsubara S., Asai S., Toyama K. and Inagaki Y.: Chart-based Parsing and Transfer in Incremental Spoken Language Translation, Proceedings of the 4th Natural Language Processing Pacific Rim Symposium, pp. 521–524 (1997).Google Scholar
- 10.Menzel, W.: Parsing of Spoken Language under Time Constraints, Proceedings of the 11th European Conference of Artificial Intellingence, pp. 560–564 (1994).Google Scholar
- 11.Landsbergen J. and Jong F.: Compositional Translation, Rosseta M. (Ed.), pp. 57–84 (1994).Google Scholar