Digital Services        F A Q

SCHOLARLY TALKS

Post-editing Machine Translation Output within a Speech-enabled CAT Tool: Findings from an Eye-tracking Study

Centre for Translation (April 20, 2023)
515









SEMINAR SERIES : Translation Seminar Series

MAJOR SPEAKER : Ciobanu, Dragoș
LENGTH : 121 min.
ACCESS : Open to all
SUMMARY : The field of Machine Translation has made significant progress in recent years, and its impact on the Language Services Industry continues to attract the attention of academics and professionals alike. However, while industry workflows have been changing and translators have had to adapt to new tasks and requirements, their computer-assisted translation (CAT) have not changed much. Our latest research project investigates a new way of working with machine translation output, designed to help mitigate the “Fluency trap” (the false sense of security given by the more fluent neural machine translation hypotheses which are not necessarily more accurate, too). In our project, professional translators worked in a CAT tool enhanced with automatic speech synthesis functionalities and completed machine translation post-editing tasks in silence, as well as with the benefit of hearing an artificial voice “speaking” the source and target text. This session will share initial findings regarding their productivity, cognitive load, and also the quality of their output.  [Go to the full record in the library's catalogue]



  ●  Persistent link: https://hkbutube.lib.hkbu.edu.hk/st/display.php?bibno=st1096
  ●  XML Dublin Core code for metadata harvesting


Recommended for You


This video is presented here with the permission of the speakers. Any downloading, storage, reproduction, and redistribution are strictly prohibited without the prior permission of the respective speakers. Go to Full Disclaimer.

  For enquiries, please contact Digital and Multimedia Services Section

© 2009-2023 All rights reserved