Name-aware language model adaptation and sparse features for statistical machine translation

Citation

W. Wang, H. Li and H. Ji, “Name-aware language model adaptation and sparse features for statistical machine translation,” in Proc. 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), p. 324.

Abstract

We propose approaches improving statistical machine translation (SMT) performance, by developing name-aware language model adaptations and sparse features, in addition to extracting nameaware translation grammar and rules, adding name phrase table, and name translation driven decoding.  Chinese-English translation experiments showed that our proposed approaches produce an absolute gain of +2.3 BLEU on top of our previous high-performing, name-aware machine translation system.

Index Terms— statistical machine translation, name translation, sparse features, language model adaptati


Read more from SRI