Using Whole Document Context in Neural Machine Translation
This addresses translation inconsistencies for users of document-level machine translation systems, though it is incremental as it builds on existing Transformer models.
The paper tackled the problem of improving translation coherence by incorporating whole-document context into neural machine translation, achieving promising results on English-German, English-French, and French-English tasks.
In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-level translation tasks. We observe interesting cross-sentential behaviors where the model learns to use document-level information to improve translation coherence.