English

Improving Neural Machine Translation by Bidirectional Training

Computation and Language 2021-09-17 v1

Abstract

We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from "src\rightarrowtgt" to "src+tgt\rightarrowtgt+src" without any complicated model modifications. Notably, our approach does not increase any parameters or training steps, requiring the parallel data merely. Experimental results show that BiT pushes the SOTA neural machine translation performance across 15 translation tasks on 8 language pairs (data sizes range from 160K to 38M) significantly higher. Encouragingly, our proposed model can complement existing data manipulation strategies, i.e. back translation, data distillation, and data diversification. Extensive analyses show that our approach functions as a novel bilingual code-switcher, obtaining better bilingual alignment.

Keywords

Cite

@article{arxiv.2109.07780,
  title  = {Improving Neural Machine Translation by Bidirectional Training},
  author = {Liang Ding and Di Wu and Dacheng Tao},
  journal= {arXiv preprint arXiv:2109.07780},
  year   = {2021}
}

Comments

EMNLP 2021. arXiv admin note: text overlap with arXiv:2107.11572

R2 v1 2026-06-24T06:01:17.501Z