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.
@article{arxiv.1704.04347,
title = {Exploiting Cross-Sentence Context for Neural Machine Translation},
author = {Longyue Wang and Zhaopeng Tu and Andy Way and Qun Liu},
journal= {arXiv preprint arXiv:1704.04347},
year = {2017}
}