Exploiting Cross-Sentence Context for Neural Machine Translation
This work addresses translation quality for users of NMT systems by incrementally enhancing context handling.
The paper tackled the problem of improving neural machine translation by incorporating cross-sentence context to resolve ambiguities, resulting in a significant improvement of up to +2.1 BLEU points over a strong baseline system.
In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on the performance of neural machine translation (NMT). First, this history is summarized in a hierarchical way. We then integrate the historical representation into NMT in two strategies: 1) a warm-start of encoder and decoder states, and 2) an auxiliary context source for updating decoder states. Experimental results on a large Chinese-English translation task show that our approach significantly improves upon a strong attention-based NMT system by up to +2.1 BLEU points.