English

Regularizing Neural Machine Translation by Target-bidirectional Agreement

Computation and Language 2018-11-14 v2

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.

Keywords

Cite

@article{arxiv.1808.04064,
  title  = {Regularizing Neural Machine Translation by Target-bidirectional Agreement},
  author = {Zhirui Zhang and Shuangzhi Wu and Shujie Liu and Mu Li and Ming Zhou and Tong Xu},
  journal= {arXiv preprint arXiv:1808.04064},
  year   = {2018}
}

Comments

Accepted by AAAI 2019

R2 v1 2026-06-23T03:31:38.641Z