Duplex Sequence-to-Sequence Learning for Reversible Machine Translation
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；UC Santa Barbara（加州大学圣塔芭芭拉分校）
英文摘要：
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 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
