Smarter edits? Post-editing with error highlights and translation suggestions

arXiv (Cornell University)

Abstract

As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights and correction suggestions based on automatic post-editing (APE). We conduct a study where professional translators (En-Nl) post-edit translations using APE error highlights and correction suggestions and compare productivity, quality and user experience to regular PE and PE with QE-derived highlights. While no condition yielded productivity or quality gains compared to regular PE, APE highlights were better received than QE-derived highlights, and correction suggestions improved overall user experience.

Authors 7

1. Fleur V. J. van Tellingen Aachen

   Leiden University

   Affiliation as printed

   Leiden University Centre for Linguistics

2. Gautam Ranka

   Visvesvaraya National Institute of Technology

   Affiliation as printed

   Visvesvaraya National Institute of Technology

3. Dora Žugčić

   Delft University of Technology

   Affiliation as printed

   Department of Bionanoscience , Faculty of Applied Sciences , Delft University of Technology

4. Joyce van der Wal

   University of Pedagogical Sciences

   Affiliation as printed

   Pedagogical Sciences , Leiden University

5. Andrea Camasta Aachen Faculty of Science, Leiden University

   Leiden University · University of Applied Sciences Leiden

   Affiliation as printed

   Faculty of Science , Leiden University

6. Livio Guerra Aachen Faculty of Science, Leiden University

   Leiden University · University of Applied Sciences Leiden

   Affiliation as printed

   Faculty of Science , Leiden University

7. Alina Karakanta Aachen

   Leiden University

   Affiliation as printed

   Leiden University Centre for Linguistics