and Machine Learnability in Computer Aided Translation
Spence Green, Sida Wang, Jason Chuang, Jerey Heer, Sebastian Schuster, Christopher D. Manning · 2014
Analysesofcomputeraidedtranslationtypically focus on either frontend interfaces and human eort, or backend translation and machine learnability of corrections. However, this distinction is artificial in practice since the frontend and backend must work in concert. We present the first holistic, quantitative evaluation of these issues by contrasting two assistive modes: postediting and interactive machine translation (MT). We describe a new translator interface, extensive modifications to a phrasebased MT system, and a novel objective function for re-tuning to human corrections. Evaluation with professional bilingualtranslatorsshowsthatpost-editisfaster than interactive at the cost of translation quality for French-English and EnglishGerman. However, re-tuning the MT system to interactive output leads to larger, statistically significant reductions in HTER versus re-tuning to post-edit. Analysis shows that tuning directly to HTER results in fine-grained corrections to subsequent machine output.