OpenTIPE: An Open-source Translation Framework for Interactive Post-Editing Research

Fabian Landwehr, Thomas Steinmann, Laura Mascarell


Abstract
Despite the latest improvements on machine translation, professional translators still must review and post-edit the automatic output to ensure high-quality translations. The research on automating this process lacks an interactive post-editing environment implemented for this purpose; therefore, current approaches do not consider the human interactions that occur in real post-editing scenarios. To address this issue, we present OpenTIPE, a flexible and extensible framework that aims at supporting research on interactive post-editing. Specifically, the interactive environment of OpenTIPE allows researchers to explore human-centered approaches for the post-editing task. We release the OpenTIPE source code and showcase its main functionalities with a demonstration video and an online live demo.
Anthology ID:
2023.acl-demo.19
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Danushka Bollegala, Ruihong Huang, Alan Ritter
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
208–216
Language:
URL:
https://aclanthology.org/2023.acl-demo.19
DOI:
10.18653/v1/2023.acl-demo.19
Bibkey:
Cite (ACL):
Fabian Landwehr, Thomas Steinmann, and Laura Mascarell. 2023. OpenTIPE: An Open-source Translation Framework for Interactive Post-Editing Research. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 208–216, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
OpenTIPE: An Open-source Translation Framework for Interactive Post-Editing Research (Landwehr et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-demo.19.pdf
Video:
 https://aclanthology.org/2023.acl-demo.19.mp4