Duplex Sequence-to-Sequence Learning for Reversible Machine Translation. NeurIPS 2021.

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 multitask-trained baselines by about 1.3 BLEU while obtaining 5.5 speedup during inference.

Jingjing Xu (许晶晶)
Jingjing Xu (许晶晶)
Postdoc

My research interests include representation learning, multilingual learning, and green (energy efficient) deep learning.