Using a Support-Vector Machine for Japanese-to-English Translation of Tense, Aspect, and Modality

TL;DR

This paper evaluates various machine learning methods for translating tense, aspect, and modality from Japanese to English, finding support-vector machines to be the most accurate among tested approaches.

Contribution

It introduces the application of support-vector machines to improve translation accuracy of tense, aspect, and modality in Japanese-English machine translation.

Findings

Support-vector machines outperformed other methods in translation accuracy.

k-nearest neighbor was previously used but less effective.

Support-vector machines achieved the highest precision in experiments.

Abstract

This paper describes experiments carried out using a variety of machine-learning methods, including the k-nearest neighborhood method that was used in a previous study, for the translation of tense, aspect, and modality. It was found that the support-vector machine method was the most precise of all the methods tested.