Modeling Coverage for Neural Machine Translation
This addresses alignment issues in NMT for machine translation systems, representing an incremental improvement.
The paper tackled the problem of over-translation and under-translation in Neural Machine Translation (NMT) caused by attention mechanisms ignoring past alignment information, and the result was a coverage-based NMT approach that significantly improved translation and alignment quality.
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.