Tagged Back-translation Revisited: Why Does It Really Work?

Benjamin Marie, Raphael Rubino, Atsushi Fujita


Abstract
In this paper, we show that neural machine translation (NMT) systems trained on large back-translated data overfit some of the characteristics of machine-translated texts. Such NMT systems better translate human-produced translations, i.e., translationese, but may largely worsen the translation quality of original texts. Our analysis reveals that adding a simple tag to back-translations prevents this quality degradation and improves on average the overall translation quality by helping the NMT system to distinguish back-translated data from original parallel data during training. We also show that, in contrast to high-resource configurations, NMT systems trained in low-resource settings are much less vulnerable to overfit back-translations. We conclude that the back-translations in the training data should always be tagged especially when the origin of the text to be translated is unknown.
Anthology ID:
2020.acl-main.532
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5990–5997
Language:
URL:
https://aclanthology.org/2020.acl-main.532
DOI:
10.18653/v1/2020.acl-main.532
Bibkey:
Cite (ACL):
Benjamin Marie, Raphael Rubino, and Atsushi Fujita. 2020. Tagged Back-translation Revisited: Why Does It Really Work?. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5990–5997, Online. Association for Computational Linguistics.
Cite (Informal):
Tagged Back-translation Revisited: Why Does It Really Work? (Marie et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.532.pdf
Video:
 http://slideslive.com/38929455