Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and under-translation. To address this problem, we propose coverage-based NMT in this paper. We maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model to help adjust future attention, which lets NMT system to consider more about untranslated source words. Experiments show that the proposed approach significantly improves both translation quality and alignment quality over standard attention-based NMT.
@article{arxiv.1601.04811,
title = {Modeling Coverage for Neural Machine Translation},
author = {Zhaopeng Tu and Zhengdong Lu and Yang Liu and Xiaohua Liu and Hang Li},
journal= {arXiv preprint arXiv:1601.04811},
year = {2016}
}
Comments
Add subjective evaluation on top of ACL version: 25% of source words are under-translated by NMT