Automatic Correction of Human Translations

Jessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker, John DeNero


Abstract
We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated systems for improving translations post-hoc with automatic post-editing. In contrast, little attention has been devoted to the problem of automatically correcting human translations, despite the intuition that humans make distinct errors that machines would be well-suited to assist with, from typos to inconsistencies in translation conventions. To investigate this, we build and release the Aced corpus with three TEC datasets (available at: github.com/lilt/tec). We show that human errors in TEC exhibit a more diverse range of errors and far fewer translation fluency errors than the MT errors in automatic post-editing datasets, suggesting the need for dedicated TEC models that are specialized to correct human errors. We show that pre-training instead on synthetic errors based on human errors improves TEC F-score by as much as 5.1 points. We conducted a human-in-the-loop user study with nine professional translation editors and found that the assistance of our TEC system led them to produce significantly higher quality revised translations.
Anthology ID:
2022.naacl-main.36
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
494–507
Language:
URL:
https://aclanthology.org/2022.naacl-main.36
DOI:
10.18653/v1/2022.naacl-main.36
Award:
 Best new task (tied) and new resource paper
Award:
 Honorable mention for contribution to special theme on human-centered NLP
Bibkey:
Cite (ACL):
Jessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker, and John DeNero. 2022. Automatic Correction of Human Translations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 494–507, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Automatic Correction of Human Translations (Lin et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.36.pdf
Code
 lilt/tec