Coverage Embedding Models for Neural Machine Translation

Haitao Mi1, Baskaran Sankaran2, Zhiguo Wang1, Abe Ittycheriah3
1IBM Watson Research Center, 2IBM T.J. Watson Research Center, 3IBM


Abstract

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a full coverage embedding vector to track the coverage status, and then keeps updating it with neural networks as the translation goes. Experiments on the large-scale Chinese-to-English task show that our enhanced model improves the translation quality significantly on various test sets over the strong large vocabulary NMT system.