Using Whole Document Context in Neural Machine Translation

2019/10/16 by Macé, Valentin, Servan, Christophe · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1910.07481

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.

Cited by

• Unlocking Latent Discourse Translation in LLMs Through Quality-Aware Decoding

Related

• Towards Making the Most of Context in Neural Machine Translation
• Document Context Neural Machine Translation with Memory Networks
• Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model
• Capturing document context inside sentence-level neural machine translation models with self-training
• Context-Adaptive Document-Level Neural Machine Translation