Quality Estimation-Assisted Automatic Post-Editing

Sourabh Deoghare, Diptesh Kanojia, Fred Blain, Tharindu Ranasinghe, Pushpak Bhattacharyya


Abstract
Automatic Post-Editing (APE) systems are prone to over-correction of the Machine Translation (MT) outputs. While Word-level Quality Estimation (QE) system can provide a way to curtail the over-correction, a significant performance gain has not been observed thus far by utilizing existing APE and QE combination strategies. In this paper, we propose joint training of a model on APE and QE tasks to improve the APE. Our proposed approach utilizes a multi-task learning (MTL) methodology, which shows significant improvement while treating both tasks as a ‘bargaining game’ during training. Moreover, we investigate various existing combination strategies and show that our approach achieves state-of-the-art performance for a ‘distant’ language pair, viz., English-Marathi. We observe an improvement of 1.09 TER and 1.37 BLEU points over a baseline QE-Unassisted APE system for English-Marathi, while also observing 0.46 TER and 0.62 BLEU points for English-German. Further, we discuss the results qualitatively and show how our approach helps reduce over-correction, thereby improving the APE performance. We also observe that the degree of integration between QE and APE directly correlates with the APE performance gain. We release our code and models publicly.
Anthology ID:
2023.findings-emnlp.115
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1686–1698
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.115
DOI:
10.18653/v1/2023.findings-emnlp.115
Bibkey:
Cite (ACL):
Sourabh Deoghare, Diptesh Kanojia, Fred Blain, Tharindu Ranasinghe, and Pushpak Bhattacharyya. 2023. Quality Estimation-Assisted Automatic Post-Editing. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1686–1698, Singapore. Association for Computational Linguistics.
Cite (Informal):
Quality Estimation-Assisted Automatic Post-Editing (Deoghare et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.115.pdf