Using Whole Document Context in Neural Machine Translation - Archive ouverte HAL Access content directly
Conference Papers Year :

Using Whole Document Context in Neural Machine Translation

Christophe Servan


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.
Fichier principal
Vignette du fichier
Mace_IWSLT2019.pdf (164.31 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02316397 , version 1 (15-10-2019)


  • HAL Id : hal-02316397 , version 1


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⟩


41 View
228 Download


Gmail Facebook Twitter LinkedIn More