A Dual Reinforcement Method for Data Augmentation using Middle Sentences for Machine Translation

Wenyi Tang, Yves Lepage


Abstract
This paper presents an approach to enhance the quality of machine translation by leveraging middle sentences as pivot points and employing dual reinforcement learning. Conventional methods for generating parallel sentence pairs for machine translation rely on parallel corpora, which may be scarce, resulting in limitations in translation quality. In contrast, our proposed method entails training two machine translation models in opposite directions, utilizing the middle sentence as a bridge for a virtuous feedback loop between the two models. This feedback loop resembles reinforcement learning, facilitating the models to make informed decisions based on mutual feedback. Experimental results substantiate that our proposed method significantly improves machine translation quality.
Anthology ID:
2023.mtsummit-research.5
Volume:
Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track
Month:
September
Year:
2023
Address:
Macau SAR, China
Editors:
Masao Utiyama, Rui Wang
Venue:
MTSummit
SIG:
Publisher:
Asia-Pacific Association for Machine Translation
Note:
Pages:
48–58
Language:
URL:
https://aclanthology.org/2023.mtsummit-research.5
DOI:
Bibkey:
Cite (ACL):
Wenyi Tang and Yves Lepage. 2023. A Dual Reinforcement Method for Data Augmentation using Middle Sentences for Machine Translation. In Proceedings of Machine Translation Summit XIX, Vol. 1: Research Track, pages 48–58, Macau SAR, China. Asia-Pacific Association for Machine Translation.
Cite (Informal):
A Dual Reinforcement Method for Data Augmentation using Middle Sentences for Machine Translation (Tang & Lepage, MTSummit 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.mtsummit-research.5.pdf