申请试用
HOT
登录
注册
 
Regularizing Neural Machine Translation by Target-bidirectional Agreement

Regularizing Neural Machine Translation by Target-bidirectional Agreement

Reboot
/
发布于
/
1974
人观看
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 up-date process. Experimental results show that our proposed method significantly outperforms state-of-the-art baselines on Chinese-English and English-German translation tasks.
3 点赞
1 收藏
0下载
相关文档
确认
3秒后跳转登录页面
去登陆