Retrieving meaning-equivalent sentences for example-based rough translation

ABSTRACT

Example-based machine translation (EBMT) is a promising translation method for speech-to-speech translation because of its robustness. It retrieves example sentences similar to the input and adjusts their translations to obtain the output. However, it has problems in that the performance degrades when input sentences are long and when the style of inputs and that of the example corpus are different. This paper proposes a method for retrieving "meaning-equivalent sentences" to overcome these two problems. A meaning-equivalent sentence shares the main meaning with an input despite lacking some unimportant information. The translations of meaning-equivalent sentences correspond to "rough translations." The retrieval is based on content words, modality, and tense.

REFERENCES

• 1: Timothy Baldwin, Low-cost, high-performance translation retrieval: dumber is better, Proceedings of the 39th Annual Meeting on Association for Computational Linguistics, p.18-25, July 06-11, 2001, Toulouse, France [doi>10.3115/1073012.1073016]
• 2: Ralf D. Brown, Automated generalization of translation examples, Proceedings of the 18th conference on Computational linguistics, p.125-131, July 31-August 04, 2000, Saarbrücken, Germany [doi>10.3115/990820.990839]
• 3: M. Carl. 1999. Inducing translation templates for example-based machine translation. In Proc. of the MT Summit VII, pages 250--258.
• 4: William B. Frakes , Ricardo Baeza-Yates, Information retrieval: data structures and algorithms, Prentice-Hall, Inc., Upper Saddle River, NJ, 1992
• 5: Daniel Jurafsky , James H. Martin, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice Hall PTR, Upper Saddle River, NJ, 2000
• 6: T. Kumano, I. Goto, H. Tanaka, N. Uratani, and T. Ehara. 2002. A translation aid system by retrieving bilingual news database. In System and Computers in Japan, pages 19--29.
• 7: Gianni Lazzari, The VI framework program in Europe: some thoughts about speech to speech translation research, Proceedings of the ACL-02 workshop on Speech-to-speech translation: algorithms and systems, p.129-135, July 11, 2002 [doi>10.3115/1118656.1118674]
• 8: Makoto Nagao, A framework of a mechanical translation between Japanese and English by analogy principle, Proc. of the international NATO symposium on Artificial and human intelligence, p.173-180, October 1984, Lyon, France
• 9: S. Ohno and M. Hamanishi, editors. 1984. Ruigo-Shin-Jiten. Kadokawa. (in Japanese).
• 10: Satoshi Sato, CTM: an example-based translation aid system, Proceedings of the 14th conference on Computational linguistics, August 23-28, 1992, Nantes, France [doi>10.3115/992424.992477]
• 11: E. Sumita and Y. Tsutsumi. 1988. A translation aid system using flexible text retrieval based on syntax-matching. In TRL Research Report TR87-1019. IBM Tokyo Research Laboratory.
• 12: Eiichiro Sumita, Example-based machine translation using DP-matching between word sequences, Proceedings of the workshop on Data-driven methods in machine translation, p.1-8, July 07-07, 2001, Toulouse, France [doi>10.3115/1118037.1118038]
• 13: T. Takezawa, E. Sumita, F. Sugaya, H. Yamamoto, and S. Yamamoto. 2002. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world. In Proc. of the 3rd LREC, pages 147--152.
• 14: T. Takezawa. 1999. Building a bilingual travel conversation database for speech translation research. In Proc. of the 2nd international workshop on East-Asian resources and evaluation conference on language resources and evaluation, pages 17--20.
• 15: Hideki Tanaka , Akio Yokoo, An efficient statistical speech act type tagging system for speech translation systems, Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, p.381-388, June 20-26, 1999, College Park, Maryland [doi>10.3115/1034678.1034738]
• 16: T. Veale and A. Way. 1997. Gaijin: A bootstrapping, template-driven approach to example-based MT. In Proc. of the NeMNLP97.
• 17: W. Wahlster, editor. 2000. Verbmobil: Foundations of Speech-to-Speech Translation. Springer.
• 18: Alex Waibel, Interactive Translation of Conversational Speech, Computer, v.29 n.7, p.41-48, July 1996 [doi>10.1109/2.511967]
• 19: Y. Wakita, K. Matsui, and Y. Sagisaka. 2000. Fine keyword clustering using a thesaurus and example sentences for speech translation. In Proc. of International Conference of Speech Language Processing, pages 390--393.
• 20: S. Yamamoto. 2000. Toward speech communications beyond language barrier - research of spoken language translation technologies at ATR -. In Proc. of ICSLP, volume 4, pages 406--411.