In a previous post I referred to the work carried out in the context of EDI-TA, with details of its objectives and main outcomes, as presented at the International Workshop on Expertise in Translation and Post-editing Research and Application (ETP), Copenhagen Business School, August 17 to August 18, 2012 (download here the presentation).
Now I refer again to this project as the final reports have been published.
- EDI-TA: Post-editing methodology for Machine Translation
- EDI-TA: Training methodology for Machine Translation Post-editing
These are two complementary deliverables (made available as Annexes I and II in Deliverable 4.1.4 within the MultilingualWeb-LT project -see here the complete list of deliverables).
EDI-TA is an R&D project conducted by Linguaserve and Universidad Europea de Madrid, as part of the tasks that Linguaserve is developing within The MultilingualWeb-LT (Language Technologies) Working Group, which belongs to the W3C Internationalization Activity and the MultilingualWeb community. The MultilingualWeb-LT Working Group receives funding by the European Commission (project name LT-Web) through the Seventh Framework Programme (FP7) Grant Agreement No. 287815. As a business oriented R&D project, EDI-TA adopted a practical outlook. Accordingly, it used Linguaserve’s resources and translation workflow for setting up an experimental scenario along the following lines:
- MT output was produced by a rule-based system (Lucy Software).
- The language pairs involved in the project were EN-ES, ES-EN, ES-EU and ES-FR.
- The number of words per language pair was 50,000.
- The text typology referred to the following areas: information on cultural events, administrative directions to the citizens, online customer information from a department store, website content from a mobile company, and advertising material from an oil company.
- A translation memory system was used as a tool for PE.