Publikation
Improving the Multi-Modal Post-Editing (MMPE) CAT Environment based on Professional Translators’ Feedback
Nico Herbig; Santanu Pal; Tim Düwel; Raksha Shenoy; Antonio Krüger; Josef van Genabith
In: Proceedings of the 1st Workshop on Post-Editing in Modern-Day Translation at AMTA. Workshop on Post-Editing in Modern-Day Translation (PEMDT-1), located at Conference of the Association for Machine Translation in the Americas (AMTA 2020), October 6-9, Orlando, Florida, USA, Pages 93-108, Association for Computational Linguistics, 10/2020.
Zusammenfassung
More and more professional translators are switching to the use of post-editing (PE) to increase productivity and reduce errors. Even though PE requires significantly less text production, current computer-aided translation (CAT) interfaces still heavily focus on traditional mouse and keyboard input and ignore other interaction modalities to support PE operations. Recently, a multi-modal post-editing (MMPE) CAT environment combining pen, touch, speech, multimodal interaction, and conventional mouse and keyboard input possibilities was presented. The design and development of the first version of MMPE were informed by extensive consultation with professional translators. This paper details how MMPE was since further refined by professional translators’ judgments on which interaction modalities are most suitable for which PE task and more general qualitative findings. In particular, we describe how the layout was adapted to avoid confusion, which visualization aids were added, how the handwriting input was improved, and how we enabled multi-word reordering through touch drag and drop, as well as how the speech and multi-modal interaction components were enhanced. Finally, we present a sneak preview of how we integrated eye tracking not only for logging but also as an input modality that can be used in combination with keyboard or speech commands.