Instance Weighting for Neural Machine Translation Domain Adaptation
2017-09-01EMNLP 2017Code Available0· sign in to hype
Rui Wang, Masao Utiyama, Lemao Liu, Kehai Chen, Eiichiro Sumita
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/wangruinlp/nmt_instance_weightingOfficialIn papernone★ 0
Abstract
Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points.