Efficient Machine Translation Corpus Generation

Kamer Ali Yuksel, Ahmet Gunduz, Shreyas Sharma, Hassan Sawaf


Abstract
This paper proposes an efficient and semi-automated method for human-in-the-loop post- editing for machine translation (MT) corpus generation. The method is based on online training of a custom MT quality estimation metric on-the-fly as linguists perform post-edits. The online estimator is used to prioritize worse hypotheses for post-editing, and auto-close best hypothe- ses without post-editing. This way, significant improvements can be achieved in the resulting quality of post-edits at a lower cost due to reduced human involvement. The trained estimator can also provide an online sanity check mechanism for post-edits and remove the need for ad- ditional linguists to review them or work on the same hypotheses. In this paper, the effect of prioritizing with the proposed method on the resulting MT corpus quality is presented versus scheduling hypotheses randomly. As demonstrated by experiments, the proposed method im- proves the lifecycle of MT models by focusing the linguist effort on production samples and hypotheses, which matter most for expanding MT corpora to be used for re-training them
Anthology ID:
2022.amta-coco4mt.2
Volume:
Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation)
Month:
September
Year:
2022
Address:
Editors:
John E. Ortega, Marine Carpuat, William Chen, Katharina Kann, Constantine Lignos, Maja Popovic, Shabnam Tafreshi
Venue:
AMTA
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
11–17
Language:
URL:
https://aclanthology.org/2022.amta-coco4mt.2
DOI:
Bibkey:
Cite (ACL):
Kamer Ali Yuksel, Ahmet Gunduz, Shreyas Sharma, and Hassan Sawaf. 2022. Efficient Machine Translation Corpus Generation. In Proceedings of the 15th biennial conference of the Association for Machine Translation in the Americas (Workshop 2: Corpus Generation and Corpus Augmentation for Machine Translation), pages 11–17, None. Association for Machine Translation in the Americas.
Cite (Informal):
Efficient Machine Translation Corpus Generation (Yuksel et al., AMTA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.amta-coco4mt.2.pdf
Code
 aixplain/Efficient-MT