Paper: Active Learning for Post-Editing Based Incrementally Retrained MT

ACL ID E14-4036
Title Active Learning for Post-Editing Based Incrementally Retrained MT
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Machine translation, in particular statis- tical machine translation (SMT), is mak- ing big inroads into the localisation and translation industry. In typical work- flows (S)MT output is checked and (where required) manually post-edited by hu- man translators. Recently, a significant amount of research has concentrated on capturing human post-editing outputs as early as possible to incrementally up- date/modify SMT models to avoid repeat mistakes. Typically in these approaches, MT and post-edits happen sequentially and chronologically, following the way unseen data (the translation job) is pre- sented. In this paper, we add to the ex- isting literature addressing the question whether and if so, to what extent, this process can be improved upon by Active Learning, where input is not present...