Outcomes

Goals

APE-QUEST will enhance CEF eTranslation with Automated Post-Editing (APE) & Quality Estimation (QE) by performing the following steps:

  • intercept eTranslation traffic
  • apply QE to distinguish between high-quality, medium-quality, and low-quality MT output
  • apply APE on medium-quality MT output
  • apply the Unbabel PE workflow on low-quality output
  • apply QE on the result of this workflow to inform downstream applications.

Papers

  • Van den Bogaert, J., Depraetere, H., Szoc, S., Vanallemeersch, T., Van Winckel, K., Everaert, F., Specia, L., Ive, J., Khalilov, M., Maroti, C., Farah, E., & Ventura A. (2019). APE-QUEST: an MT Quality Gate. In Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks (pp. 110-111).
  • Van den Bogaert, J., Depraetere, H., Szoc, S., Vanallemeersch, T., Specia, L., Ive, J., & Khalilov, M. (2020). APE-QUEST: a Quality Gate for Routing MT. In Proceedings of EAMT 2020 (pp. 473-474).
  • Szoc, Sara, Heidi Depraetere (2020). Quality Estimation, In: Jörg Porsiel (Hg., 2020): Maschinelle Übersetzung für Übersetzungsprofis. Berlin: BDÜ Fachverlag. Sammelband mit Beiträgen in deutscher und englischer Sprache. 384 Seiten, ISBN: 9783946702092.
  • Ive, J., Specia, L., Szoc, S., Vanallemeersch, T., Van den Bogaert, J., Farah, E., Maroti, C., Ventura, A. & Khalilov, M. (2020) A Post-Editing Dataset in the Legal Domain: Do we Underestimate Neural Machine Translation Quality? In Proceedings of LREC 2020.
  • Heidi Depraetere, Joachim Van den Bogaert, Sara Szoc and Tom Vanallemeersch (2020). APE-QUEST: a Quality Gate for Routing MT. In Proceedings of EAMT 2020.