Conference paper Open Access

Using Whole Document Context in Neural Machine Translation

Macé, Valentin; Servan, Christophe

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.

Files (168.3 kB)
Name Size
IWSLT2019_paper_20.pdf
md5:3a4a4614e5f77e181163dafd99370339
168.3 kB Download
78
64
views
downloads
All versions This version
Views 7878
Downloads 6464
Data volume 10.8 MB10.8 MB
Unique views 7373
Unique downloads 5858

Share

Cite as