Thomas Steinmann
2023
OpenTIPE: An Open-source Translation Framework for Interactive Post-Editing Research
Fabian Landwehr
|
Thomas Steinmann
|
Laura Mascarell
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
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.