Towards User-Driven Neural Machine Translation

Huan Lin, Liang Yao, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Degen Huang, Jinsong Su


Abstract
A good translation should not only translate the original content semantically, but also incarnate personal traits of the original text. For a real-world neural machine translation (NMT) system, these user traits (e.g., topic preference, stylistic characteristics and expression habits) can be preserved in user behavior (e.g., historical inputs). However, current NMT systems marginally consider the user behavior due to: 1) the difficulty of modeling user portraits in zero-shot scenarios, and 2) the lack of user-behavior annotated parallel dataset. To fill this gap, we introduce a novel framework called user-driven NMT. Specifically, a cache-based module and a user-driven contrastive learning method are proposed to offer NMT the ability to capture potential user traits from their historical inputs under a zero-shot learning fashion. Furthermore, we contribute the first Chinese-English parallel corpus annotated with user behavior called UDT-Corpus. Experimental results confirm that the proposed user-driven NMT can generate user-specific translations.
Anthology ID:
2021.acl-long.310
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:
4008–4018
Language:
URL:
https://aclanthology.org/2021.acl-long.310
DOI:
10.18653/v1/2021.acl-long.310
Bibkey:
Cite (ACL):
Huan Lin, Liang Yao, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Degen Huang, and Jinsong Su. 2021. Towards User-Driven Neural Machine 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 4008–4018, Online. Association for Computational Linguistics.
Cite (Informal):
Towards User-Driven Neural Machine Translation (Lin et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.310.pdf
Video:
 https://aclanthology.org/2021.acl-long.310.mp4
Code
 DeepLearnXMU/User-Driven-NMT