Coverage Embedding Models for Neural Machine Translation
This work addresses translation errors in NMT for language pairs like Chinese-English, but it is incremental as it builds on existing attention-based methods.
The paper tackles the problem of repeating and dropping translations in neural machine translation by adding explicit coverage embedding models to attention-based NMT, resulting in significant improvements in translation quality on a large-scale Chinese-to-English task.
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.