人工知能学会論文誌
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
原著論文
機械翻訳システムの出力安定性の評価
髙橋 寛治竹野 峻輔山本 和英
著者情報
ジャーナル フリー

2017 年 32 巻 5 号 p. D-H33_1-4

詳細
抄録

This paper presents a novel metric for evaluating stability of machine translation system. A stable system indicates that it keeps almost the same outputs given the inputs with slight changes. In this paper, we propose a stability metric by exploiting TER metric for evaluating the differences between the two texts. We have built an evaluation data set, and demonstrate that a neural-based method is unstable rather than a statistical-based method, while the former outperforms the latter.

著者関連情報
© 人工知能学会 2017
前の記事 次の記事
feedback
Top