Using a support-vector machine for Japanese-to-English translation of tense, aspect, and modality
DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
Hi-index | 0.00 |
Senseval-2 was held in Spring, 2001. It consisted of several tasks in various languages. In this paper, we describe our system used for one of these tasks: the Japanese translation task. With an accuracy of 63.4%, our system was the third best system in the contest among nine systems developed by seven groups.