Improving Back-Translation with Uncertainty-based Confidence Estimation

Shuo Wang, Yang Liu, Chao Wang, Huanbo Luan, Maosong Sun


Abstract
While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy. In this work, we propose to quantify the confidence of NMT model predictions based on model uncertainty. With word- and sentence-level confidence measures based on uncertainty, it is possible for back-translation to better cope with noise in synthetic bilingual corpora. Experiments on Chinese-English and English-German translation tasks show that uncertainty-based confidence estimation significantly improves the performance of back-translation.
Anthology ID:
D19-1073
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
791–802
Language:
URL:
https://aclanthology.org/D19-1073
DOI:
10.18653/v1/D19-1073
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/D19-1073.pdf
Code
 THUNLP-MT/UCE4BT