Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

Zaixiang Zheng, Hao Zhou, Shujian Huang, Jiajun Chen, Jingjing Xu, Lei Li

Keywords: duplex network, sequence-to-sequence learning, reversible machine translation

Abstract: Sequence-to-sequence learning naturally has two directions. How to effectively utilize supervision signals from both directions? Existing approaches either require two separate models, or a multitask-learned model but with inferior performance. In this paper, we propose REDER (Reversible Duplex Transformer), a parameter-efficient model and apply it to machine translation. Either end of REDER can simultaneously input and output a distinct language. Thus REDER enables {\em reversible machine translation} by simply flipping the input and output ends. Experiments verify that REDER achieves the first success of reversible machine translation, which helps outperform its multitask-trained baselines by up to 1.3 BLEU.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/zhengzx-nlp/REDER

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2105.03458/code)