Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016
This work addresses translation quality for Japanese-English tasks, representing an incremental improvement in NMT methods.
The paper tackled improving neural machine translation for Japanese-English by incorporating discrete translation lexicons and minimum risk training, resulting in the highest BLEU scores in the WAT2016 competition.
This year, the Nara Institute of Science and Technology (NAIST)/Carnegie Mellon University (CMU) submission to the Japanese-English translation track of the 2016 Workshop on Asian Translation was based on attentional neural machine translation (NMT) models. In addition to the standard NMT model, we make a number of improvements, most notably the use of discrete translation lexicons to improve probability estimates, and the use of minimum risk training to optimize the MT system for BLEU score. As a result, our system achieved the highest translation evaluation scores for the task.