Detector–Corrector: Edit-Based Automatic Post Editing for Human Post Editing

Hiroyuki Deguchi, Masaaki Nagata, Taro Watanabe


Abstract
Post-editing is crucial in the real world because neural machine translation (NMT) sometimes makes errors.Automatic post-editing (APE) attempts to correct the outputs of an MT model for better translation quality.However, many APE models are based on sequence generation, and thus their decisions are harder to interpret for actual users.In this paper, we propose “detector–corrector”, an edit-based post-editing model, which breaks the editing process into two steps, error detection and error correction.The detector model tags each MT output token whether it should be corrected and/or reordered while the corrector model generates corrected words for the spans identified as errors by the detector.Experiments on the WMT’20 English–German and English–Chinese APE tasks showed that our detector–corrector improved the translation edit rate (TER) compared to the previous edit-based model and a black-box sequence-to-sequence APE model, in addition, our model is more explainable because it is based on edit operations.
Anthology ID:
2024.eamt-1.18
Volume:
Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2024
Address:
Sheffield, UK
Editors:
Carolina Scarton, Charlotte Prescott, Chris Bayliss, Chris Oakley, Joanna Wright, Stuart Wrigley, Xingyi Song, Edward Gow-Smith, Rachel Bawden, Víctor M Sánchez-Cartagena, Patrick Cadwell, Ekaterina Lapshinova-Koltunski, Vera Cabarrão, Konstantinos Chatzitheodorou, Mary Nurminen, Diptesh Kanojia, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation (EAMT)
Note:
Pages:
191–206
Language:
URL:
https://aclanthology.org/2024.eamt-1.18
DOI:
Bibkey:
Cite (ACL):
Hiroyuki Deguchi, Masaaki Nagata, and Taro Watanabe. 2024. Detector–Corrector: Edit-Based Automatic Post Editing for Human Post Editing. In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), pages 191–206, Sheffield, UK. European Association for Machine Translation (EAMT).
Cite (Informal):
Detector–Corrector: Edit-Based Automatic Post Editing for Human Post Editing (Deguchi et al., EAMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eamt-1.18.pdf