Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation

Weijia Xu, Xing Niu, Marine Carpuat


Abstract
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared. We introduce a novel dual reconstruction objective that provides a unified view of Iterative Back-Translation and Dual Learning. It motivates a theoretical analysis and controlled empirical study on German-English and Turkish-English tasks, which both suggest that Iterative Back-Translation is more effective than Dual Learning despite its relative simplicity.
Anthology ID:
2020.findings-emnlp.182
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2006–2020
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.182
DOI:
10.18653/v1/2020.findings-emnlp.182
Bibkey:
Cite (ACL):
Weijia Xu, Xing Niu, and Marine Carpuat. 2020. Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2006–2020, Online. Association for Computational Linguistics.
Cite (Informal):
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation (Xu et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.182.pdf