ICASSP 2022accepted0 citations

Context-Adaptive Document-Level Neural Machine Translation

Linlin Zhang, Zhirui Zhang, Boxing Chen, Weihua Luo, Luo Si

Abstract

Document-level translation models are still far from perfect. Most existing document-level neural machine translation (NMT) models leverage a fixed number of the previous or all global sentences to handle the context-independent problem in standard NMT. However, the translating of each source sentence benefits from various sizes of context. And study shows that inappropriate redundant context will increase model burden but not improve the translation performance. This work introduces a data-adaptive method that enables the model to adopt the necessary and helpful context. Specifically, we introduce a light predictor into two document-level translation models to select the explicit context. Experiments demonstrate the proposed approach can significantly improve the performance over the previous methods with a gain up to 1.99 BLEU points.

BibTeX
@inproceedings{icassp2022_contextadaptived,
  title = {Context-Adaptive Document-Level Neural Machine Translation},
  author = {Linlin Zhang and Zhirui Zhang and Boxing Chen and Weihua Luo and Luo Si},
  booktitle = {ICASSP 2022},
  year = {2022}
}
Context-Adaptive Document-Level Neural Machine Translation · ICASSP 2022