Efficient Bidirectional Neural Machine Translation

By Xu Tan, Yingce Xia, Lijun Wu, Tao Qin. 2019

5 citations recorded by the source corpus.

The encoder-decoder based neural machine translation usually generates a target sequence token by token from left to right. Due to error propagation, the tokens in the right side of the generated sequence are usually of poorer quality than those in the left side. In this paper, we propose an efficient method to generate a sequence in both left-to-right and right-to-left manners using a single encoder and decoder, combining the advantages of both generation directions. Experiments on three translation tasks show that our method achieves significant improvements over conventional unidirectional approach. Compared with ensemble methods that train and combine two models with different generation directions, our method saves 50% model parameters and about 40% training time, and also improve inference speed.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Sheng Zhao
6. Yi Ren
7. Zhou Zhao
8. Lei He

In Computer Vision and Pattern Recognition

1. Tie-Yan Liu
2. Tao Qin
3. Xu Tan
4. Frank K. Soong
5. Yingce Xia
6. Di He
7. Lijun Wu
8. Hang Li

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “Considering the right part of the generated mel-spectrogram sequence is usually worse than than that in the left part due to error propagation, some works leverage both left-to-right and right-to-left generations [338] for data augmentation [285] and regularization [445].”