Publication Abstract

Lee, Y. S., W. Yi, S., Seneff, S., Weinstein, C. J., Interlingua-Based Broad-Coverage Korean-to-English Document in CCLINC, Proceedings of HLT 2001, First International Conference on Human Language Technology Research, J. Allan, ed., Morgan Kaufmann, San Francisco, 2001.

Abstract

At MIT Lincoln Laboratory, we have been developing a Korean-to-English machine translation system, CCLINC (Common Coalition Language System at Lincoln Laboratory)s. The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language-neutral meaning representation called a semantic frame. The key features of the CCLINC Korean-to-English translation system include: (1) Robust, efficient parsing of Korean (a verb-final language with overt case markers, relatively free word order, and frequent omission of arguments); (2) high-quality translation via word sense disambiguation and accurate word order generation of the target language; (3) rapid system development and porting to new domains via knowledge-based, automated acquisition of grammars. Having been trained on Korean newspaper articles on "missiles" and "chemical biological warfare," the system achieves about 60% translation accuracy on the training data and about 50% translation accuracy on the test data.