Adapting Neural Machine Translation for Automatic Post-Editing

Abhishek Sharma, Prabhakar Gupta, Anil Nelakanti


Abstract
Automatic post-editing (APE) models are usedto correct machine translation (MT) system outputs by learning from human post-editing patterns. We present the system used in our submission to the WMT’21 Automatic Post-Editing (APE) English-German (En-De) shared task. We leverage the state-of-the-art MT system (Ng et al., 2019) for this task. For further improvements, we adapt the MT model to the task domain by using WikiMatrix (Schwenket al., 2021) followed by fine-tuning with additional APE samples from previous editions of the shared task (WMT-16,17,18) and ensembling the models. Our systems beat the baseline on TER scores on the WMT’21 test set.
Anthology ID:
2021.wmt-1.35
Volume:
Proceedings of the Sixth Conference on Machine Translation
Month:
November
Year:
2021
Address:
Online
Venues:
EMNLP | WMT
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
315–319
Language:
URL:
https://aclanthology.org/2021.wmt-1.35
DOI:
Bibkey:
Cite (ACL):
Abhishek Sharma, Prabhakar Gupta, and Anil Nelakanti. 2021. Adapting Neural Machine Translation for Automatic Post-Editing. In Proceedings of the Sixth Conference on Machine Translation, pages 315–319, Online. Association for Computational Linguistics.
Cite (Informal):
Adapting Neural Machine Translation for Automatic Post-Editing (Sharma et al., WMT 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wmt-1.35.pdf
Data
WMT 2016WikiMatrix