Using Whole Document Context in Neural Machine Translation

Abstract

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.

Accepted paper to IWSLT2019

References in corpus (3)

• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Does Neural Machine Translation Benefit from Larger Context?

Cited by in corpus (6)

• A Survey on Document-level Neural Machine Translation: Methods and Evaluation
• Document Graph for Neural Machine Translation
• Document-level Neural Machine Translation with Document Embeddings
• Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation
• Revisiting Context Choices for Context-aware Machine Translation
• Document-level Neural Machine Translation with Associated Memory Network