Multilingual Access to Educational Material Through Contributive Post-editing of MT Pre-translations by Foreign Students

  • Ruslan KalitvianskiEmail author
  • Valérie Bellynck
  • Christian Boitet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9412)


In our teaching practice, we often observe that, due to the lack of prerequisites and limited mastery of a language, foreign students face difficulties in understanding course contents. This especially burdens students from Eastern and South-Eastern Asia, because of the distance between their native languages and the instructional language (French in our case). We propose a quick and cost-effective method for making educational content accessible in the native tongues of the students, through a contributive computer-assisted multilingualization by voluntary participants. The process consists in post-editing MT (Machine Translation) pre-translations via an interactive multilingual access gateway (iMAG), which displays a web page in a selected language. Since 2012, several students have validated the approach by producing in Chinese more than 500 pages (125 K words) of French undergraduate and graduate course material about computer science, at a rate of about 10 min (total time) per standard page. This multilingual resource is freely accessible on the MACAU-Chamilo platform.


Multilingual access Educational material Computer-assisted translation Post-editing 


  1. 1.
    Green, S., Heer, J., Manning, C.D.: The efficacy of human post-editing for language translation. In: Proceedings of ACM Human Factors in Computing Systems (2013)Google Scholar
  2. 2.
    Tarasowa, D., Khalili, A., Auer, S., Unbehauen, J.: CrowdLearn: crowd-sourcing the creation of highly-structured e-learning content. In: 5th International Conference on Computer-Supported Education CSEDU 2013 (2013)Google Scholar
  3. 3.
    Boitet, C., Phap, H.C., Nguyen, H.T., Bellynck, V.: The iMAG concept: multilingual access gateway to an elected web sites with incremental quality increase through collaborative post-edition of MT pretranslations. In: TALN-2010, 8 p (2010)Google Scholar
  4. 4.
    Besacier, L.: Traduction automatisée d’une œuvre littéraire: une étude pilote. Traitement Automatique du Langage Naturel (TALN), juillet 2014, Marseille, France (2014)Google Scholar
  5. 5.
    Wang, L., Boitet, C.: Online production of HQ parallel corpora and permanent task-based evaluation of multiple MT systems: both can be obtained through iMAGs with no added cost. In: Proceedings of MT Summit XIV, the 2nd Workshop on Post-editing Technologies and Practice (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Ruslan Kalitvianski
    • 1
    • 2
    Email author
  • Valérie Bellynck
    • 2
  • Christian Boitet
    • 2
  1. 1.Viseo TechnologiesGrenobleFrance
  2. 2.LIG-GETALPSaint Martin d’HèresFrance

Personalised recommendations