MET workshops

Getting to grips with post-editing machine translation

To meet the growing demand for translation, post-editing of machine translation output (PEMT) is being increasingly adopted as a mainstream alternative working method. The compelling reason behind this trend is the widely reported increase in productivity compared to human translation together with a comparable and sometimes higher quality level. The skills required for post-editing are different from those needed for the editing of author-written texts and different from those required for translation. This workshop aims to familiarize attendees with post-editing methods by analysing the typical mistakes of both neural and statistical machine translation (MT). It also provides some insight into why certain errors occur in raw MT output through a presentation of the historical development of the technology. It will conclude with a discussion of when PEMT should and should not be used and how raw MT output can be improved through preparatory steps.

Developer and facilitator: Michael Farrell

Purpose: To familiarize attendees with post-editing methods and techniques, and put them in a position to judge which kinds of text can be profitably dealt with in this way rather than by human translation.

Description and structure: The workshop will consist of
  • a brief history of the development of MT technology
  • post-editing guidelines
  • a challenge between post-editing and human translation
  • illustration of the stink of MT
  • detection and classification of typical MT errors
  • techniques to improve the quality of raw MT output
There will be two practical experiments to be performed with your laptop/tablet, which attendees must therefore bring with them (possibly with power cables). No special software is required other than a common word processor. The first experiment is against the clock: half the group will translate short texts from various languages into English or vice versa and the other half will post-edit machine-translated versions of the same texts. The results will then be compared. The second is a post-editing exercise from Italian or Spanish into English, or English into Italian or Spanish. Attendees will be asked to detect errors in the raw MT output and use the knowledge they have gained to categorize and correct them.

Who should attend? Anyone who would like to find out more about post-editing.

Outcome skills: Attendees will have gained insight into the skills required to become post-editors and be able to judge whether to offer post-editing as a service or incorporate it into their normal working processes.

Pre-workshop information: Attendees are encouraged to carry out experiments by feeding texts written in their normal non-English working languages into the free online MT engines (Google Translate, Microsoft Translator, DeepL, etc.) and singling out the recurrent and/or apparently inexplicable mistakes that occur in the English raw output. The facilitator would be more than pleased to receive typical, interesting and/or particularly amusing examples by email before the workshop so that they may be added to the workshop material for all to appreciate.
About the facilitator: Michael Farrell is an untenured lecturer in post-editing, machine translation and computer tools for translators at the International University of Languages and Media (IULM), Milan, Italy; the developer of the terminology search tool IntelliWebSearch; a qualified member of the Italian Association of Translators and Interpreters (AITI); and neo-member of MET Council.

Besides this, he is a freelance translator and transcreator. Over the years, he has acquired experience in the cultural tourism field and in transcreating advertising copy and press releases, chiefly for the promotion of technology products. Being a keen amateur cook, he also translates texts on Italian cuisine.