papers AI Learner
The Github is limit! Click to go to the new site.

Regularizing Neural Machine Translation by Target-bidirectional Agreement

2018-11-12
Zhirui Zhang, Shuangzhi Wu, Shujie Liu, Mu Li, Ming Zhou, Tong Xu

Abstract

Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation process are fed as inputs to the model and can be quickly amplified, harming subsequent sequence generation. To address this issue, we propose a novel model regularization method for NMT training, which aims to improve the agreement between translations generated by left-to-right (L2R) and right-to-left (R2L) NMT decoders. This goal is achieved by introducing two Kullback-Leibler divergence regularization terms into the NMT training objective to reduce the mismatch between output probabilities of L2R and R2L models. In addition, we also employ a joint training strategy to allow L2R and R2L models to improve each other in an interactive update process. Experimental results show that our proposed method significantly outperforms state-of-the-art baselines on Chinese-English and English-German translation tasks.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1808.04064

PDF

https://arxiv.org/pdf/1808.04064


Comments

Content