Publication Abstract

Weinstein, C. J., Lee, Y. S., Seneff, S., Tummala, D. R., Carlson, B., Lynch, J. T., Hwang, J. T., and Kukolich, L. C., Automated English/Korean Translation for Enhanced Coalition Communications, Lincoln Laboratory Journal, Vol. 10, No. 1, pp. 35-60, 1997.

Abstract

This article describes our work-in-progress on automated, two-way, English/Korean translation of text and speech for enhanced coalition communications. Our ultimate goal is to enhance multilingual communications by producing accurate translations across a number of languages. Therefore, we have chosen an interlingua-based approach to machine translation that is readily extendable to multiple languages. In this approach, a natural language understanding system transforms the input into an intermediate meaning representation called a semantic frame, which can serve as the basis for generation of output in multiple languages. To produce useful, accurate, and effective translation systems in the short term, we have focused on limited military task domains and have configured our system as a translator's aid, so that the human translator can confirm or edit the machine translation. We have obtained promising results in translation of telegraphic military messages in a naval domain, and have successfully extended the system to additional military domains. The system has been demonstrated in a coalition exercise and at Combined Forces Command in the Republic of Korea. One key lesson from those efforts is that the system must be robust in handling new inputs, and we have developed a multi-stage robust translation strategy, including a part-of-speech tagging technique to handle new words and a fragmentation strategy for handling complex sentences. Current work is focused on ongoing development of these robustness techniques and on porting the translation system to application domains of specific interest to the users in the coalition environment in the Republic of Korea.