Modeling Coverage for Neural Machine Translation Article Swipe

PDF

Related Concepts

Machine translation Translation (biology) Computer science Artificial intelligence Quality (philosophy) Mechanism (biology) Machine learning Track (disk drive) Natural language processing Epistemology Messenger RNA Gene Operating system Chemistry Philosophy Biochemistry

Zhaopeng Tu , Zhengdong Lu , Yang Liu , Xiaohua Liu , Hang Li ·

YOU? · · 2016 · Open Access · · DOI: https://doi.org/10.48550/arxiv.1601.04811 · OA: W2410539690

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.

Modeling Coverage for Neural Machine Translation Article Swipe

Related Topics