Bridging the Gap between Training and Inference for Neural Machine Translation

Wen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu


This paper proposes a method to improve the task of Neural Machine Translation by sampling for context words…..predicted words along with ground truth words, choosing the predicted words on either a word-based level or at a sentence level. This paper also got the best Long paper award at ACL 2019

Model and Concepts

Main Conclusions and Results

Our Two Cents