Vergleich der menschlichen, maschinellen und Post-Editing-Übersetzung aus dem Slowakischen ins Deutsche mittels automatischer Evaluation

Abstract

SummaryThe aim of the study is to compare translation quality and effectiveness (translator productivity) using measures of the automatic evaluation of machine translation output. The examined translation(s) was a legal text, translated from Slovak (mother tongue) into German. We distinguish human translation (HT), machine translation (MT) and post-edited MT (PEMT). For the evaluation we used our own tool, wherein were implemented the metrics of automatic MT evaluation. Analysis of Variance and Multiply Comparisons (Tukey HSD test) were applied to textual data. The results proved that in terms of productivity, regarding the expert and terminological knowledge of human translators, post-editing of MT is more effective than HT. On the other hand, in terms of quality (sentence structure or stylistics), regardless of time, HT is of a higher quality then MT, but similar to PEMT. The post-editors were affected by grammar and by stylistics of MT output, but post-edited a larger volume of MT than human translators translated.