Incorporating Terminology Constraints in Automatic Post-Editing

David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, Kathleen McKeown


Abstract
Users of machine translation (MT) may want to ensure the use of specific lexical terminologies. While there exist techniques for incorporating terminology constraints during inference for MT, current APE approaches cannot ensure that they will appear in the final translation. In this paper, we present both autoregressive and non-autoregressive models for lexically constrained APE, demonstrating that our approach enables preservation of 95% of the terminologies and also improves translation quality on English-German benchmarks. Even when applied to lexically constrained MT output, our approach is able to improve preservation of the terminologies. However, we show that our models do not learn to copy constraints systematically and suggest a simple data augmentation technique that leads to improved performance and robustness.
Anthology ID:
2020.wmt-1.141
Volume:
Proceedings of the Fifth Conference on Machine Translation
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1193–1204
Language:
URL:
https://aclanthology.org/2020.wmt-1.141
DOI:
Bibkey:
Cite (ACL):
David Wan, Chris Kedzie, Faisal Ladhak, Marine Carpuat, and Kathleen McKeown. 2020. Incorporating Terminology Constraints in Automatic Post-Editing. In Proceedings of the Fifth Conference on Machine Translation, pages 1193–1204, Online. Association for Computational Linguistics.
Cite (Informal):
Incorporating Terminology Constraints in Automatic Post-Editing (Wan et al., WMT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.wmt-1.141.pdf
Video:
 https://slideslive.com/38939650
Code
 zerocstaker/constrained_ape
Data
eSCAPE