文章基本信息

标题：Max Margin Learning for Statistical Machine Translation Toward Improvement of Machine Translation Accuracy
本地全文：下载
作者：Katsuhiko Hayashi ; Taro Watanabe ; Hajime Tsukada 等
期刊名称：人工知能学会論文誌
印刷版ISSN：1346-0714
电子版ISSN：1346-8030
出版年度：2010
卷号：25
期号：5
页码：593-601
DOI：10.1527/tjsai.25.593
出版社：The Japanese Society for Artificial Intelligence
摘要：Minimum error rate training (MERT) has been a widely used learning method for statistical machine translation to estimate the feature function weights of a linear model. MERT has an advantage to incorpolate an automatic translation evaluation metrics as BLEU scores to its objective function. Weight vector can directly be optimized with Line search algorithm using error surface on a given set of candidate translations. It efficiently searches the best parameter resulting the highest BLEU scores. In this paper, we presented a new training algorithm for statisitcal machine translation, inspired by MERT and Structural Support Vector Machines. We performed MERT optimization by maximizing the margin between the oracle and incorrect translations under the L2-norm prior. Our experimental results on Japanese-English speech translation task showed that BLEU scores obtained by our proposed method were much better than those obtained by MERT. We achieved the best improvement of BLEU about +3.0 over standard MERT.
关键词：Support Vector Machines ; Statistical Machine Translation ; Minimum Error Rate Training ; machine learning