Controlling Styles in Neural Machine Translation with Activation Prompt

Yifan Wang, Zewei Sun, Shanbo Cheng, Weiguo Zheng, Mingxuan Wang

Abstract
Controlling styles in neural machine translation (NMT) has attracted wide attention, as it is crucial for enhancing user experience. Earlier studies on this topic typically concentrate on regulating the level of formality and achieve some progress in this area. However, they still encounter two major challenges. The first is the difficulty in style evaluation. The style comprises various aspects such as lexis, syntax, and others that provide abundant information. Nevertheless, only formality has been thoroughly investigated. The second challenge involves excessive dependence on incremental adjustments, particularly when new styles are necessary. To address both challenges, this paper presents a new benchmark and approach. A multiway stylized machine translation (MSMT) benchmark is introduced, incorporating diverse categories of styles across four linguistic domains. Then, we propose a method named style activation prompt (StyleAP) by retrieving prompts from stylized monolingual corpus, which does not require extra fine-tuning. Experiments show that StyleAP could effectively control the style of translation and achieve remarkable performance.
Anthology ID:
2023.findings-acl.163
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2606–2620
Language:
URL:
https://aclanthology.org/2023.findings-acl.163
DOI:
10.18653/v1/2023.findings-acl.163
Bibkey:
Cite (ACL):
Yifan Wang, Zewei Sun, Shanbo Cheng, Weiguo Zheng, and Mingxuan Wang. 2023. Controlling Styles in Neural Machine Translation with Activation Prompt. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2606–2620, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Controlling Styles in Neural Machine Translation with Activation Prompt (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.findings-acl.163.pdf
PDF Search