Example-based Translation of Japanese Functional Expressions utilizing Semantic Equivalence Classes

This paper studies issues on machine translation of Japanese functional expressions into English. Unlike our previous works, in order to address the issue of resolving various ambiguities of a compound expression, this paper takes the approach of example-based machine translation. In this approach, a patent translation example database is developed given the phrase translation tables trained with parallel patent sentences as well as the training parallel patent sentences themselves. When identifying the most similar translation examples, we integrate semantic equivalence classes of Japanese functional expressions as well as more fine-grained similarity measure of translation examples. In the evaluation, we compare the translation accuracy of the proposed framework with that of Moses, and show that the proposed framework somehow outperforms Moses.