Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations

Baikjin Jung, Myungji Lee, Jong-Hyeok Lee, Yunsu Kim


Abstract
Automatic postediting (APE) is an automated process to refine a given machine translation (MT). Recent findings present that existing APE systems are not good at handling high-quality MTs even for a language pair with abundant data resources, English–German: the better the given MT is, the harder it is to decide what parts to edit and how to fix these errors. One possible solution to this problem is to instill deeper knowledge about the target language into the model. Thus, we propose a linguistically motivated method of regularization that is expected to enhance APE models’ understanding of the target language: a loss function that encourages symmetric self-attention on the given MT. Our analysis of experimental results demonstrates that the proposed method helps improving the state-of-the-art architecture’s APE quality for high-quality MTs.
Anthology ID:
2023.acl-short.122
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1433–1441
Language:
URL:
https://aclanthology.org/2023.acl-short.122
DOI:
10.18653/v1/2023.acl-short.122
Bibkey:
Cite (ACL):
Baikjin Jung, Myungji Lee, Jong-Hyeok Lee, and Yunsu Kim. 2023. Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1433–1441, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations (Jung et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-short.122.pdf
Video:
 https://aclanthology.org/2023.acl-short.122.mp4