CTM: an example-based translation aid system

ABSTRACT

This paper describes a Japanese-English translation aid system, CTM, which has a useful capability for flexible retrieval of texts from bilingual corpora or translation databases. Translation examples (pairs of a text and its translation equivalent) are very helpful for us to translate the similar text. Our character-based best match retrieval method can retrieve translation examples similar to the given input. This method has the following advantages: (1) this method accepts free-style translation examples, i.e., pairs of any text string and its translation equivalent, (2) morphological analysis is unneccessary, (3) this method accepts free-style inputs (i.e., any text strings) for retrieval. We show the retrieval examples with the following characteristic features: phrasal expression, long-distance dependency, idiom, synonym, and semantic ambiguity.

REFERENCES

• 1: William A. Gale , Kenneth W. Church, A program for aligning sentences in bilingual corpora, Proceedings of the 29th annual meeting on Association for Computational Linguistics, p.177-184, June 18-21, 1991, Berkeley, California [doi>10.3115/981344.981367]
• 2: Ikehara, S.: Test Sentences for Evaluating Japanese-English Machine Translation, (in Japanese), NTT, 1991.
• 3: Michalski, R., Carbonell, J. and Mitchell, T. (Eds.): Machine Learning, Tioga Publishing Company, 1983.
• 4: Nagao, M. et al (Eds): Iwanami Encyclopedic Dictionary of Computer Science, (in Japanese), Iwanami Shoten, 1990.
• 5: Nakamura, N.: Translation Support by Retrieving Bilingual Texts, (in Japanese), Proc. of 38th Convention of IPSJ, pp. 357--358, 1989.
• 6: Sato, S.: Example-Based Translation Approach, Proc. of International Workshop on Fundamental Research for the Future Generation of Natural Language Processing, ATR Interpreting Telephony Research Laboratories, pp. 1--16, 1991.
• 7: Shimizu and Narita (Eds.): The Kodansha Japanese-English Dictionary, Koudansha, 1976.
• 8: Sumita, E. and Tsutsumi, Y.: A Translation Aid System Using Flexible Text Retrieval Based on Syntax-Matching, TRI. Reseach Report, TR-87-1019, Tokyo Research Laboratory, IBM, 1988.