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.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02316397
Contributor : Christophe Servan <>
Submitted on : Tuesday, October 15, 2019 - 11:47:46 AM
Last modification on : Saturday, October 19, 2019 - 1:30:58 AM

Files

Mace_IWSLT2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02316397, version 1

Collections

Citation

Valentin Macé, Christophe Servan. Using Whole Document Context in Neural Machine Translation. 16th International Workshop on Spoken Language Translation 2019, Nov 2019, Hong-Kong, China. ⟨hal-02316397⟩

Share

Metrics

Record views

5

Files downloads

13