Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation

Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, Zhaopeng Tu


Abstract
Knowledge distillation (KD) is commonly used to construct synthetic data for training non-autoregressive translation (NAT) models. However, there exists a discrepancy on low-frequency words between the distilled and the original data, leading to more errors on predicting low-frequency words. To alleviate the problem, we directly expose the raw data into NAT by leveraging pretraining. By analyzing directed alignments, we found that KD makes low-frequency source words aligned with targets more deterministically but fails to align sufficient low-frequency words from target to source. Accordingly, we propose reverse KD to rejuvenate more alignments for low-frequency target words. To make the most of authentic and synthetic data, we combine these complementary approaches as a new training strategy for further boosting NAT performance. We conduct experiments on five translation benchmarks over two advanced architectures. Results demonstrate that the proposed approach can significantly and universally improve translation quality by reducing translation errors on low-frequency words. Encouragingly, our approach achieves 28.2 and 33.9 BLEU points on the WMT14 English-German and WMT16 Romanian-English datasets, respectively. Our code, data, and trained models are available at https://github.com/longyuewangdcu/RLFW-NAT.
Anthology ID:
2021.acl-long.266
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3431–3441
Language:
URL:
https://aclanthology.org/2021.acl-long.266
DOI:
10.18653/v1/2021.acl-long.266
Bibkey:
Cite (ACL):
Liang Ding, Longyue Wang, Xuebo Liu, Derek F. Wong, Dacheng Tao, and Zhaopeng Tu. 2021. Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3431–3441, Online. Association for Computational Linguistics.
Cite (Informal):
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation (Ding et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.266.pdf
Video:
 https://aclanthology.org/2021.acl-long.266.mp4
Code
 alphadl/rlfw-nat