ScholarWorks@숙명여자대학교

초록

This research investigates the nature of English to Korean full post-editing and what factors can affect the productivity of full post-editing. The first goal is to examine if machine translation post-editing is faster than human translation and if the adequacy and fluency are not inferior to human translation. The data collected from 14 students showed that full post-editing is 69.66% faster than human translation. A sampling evaluation found that post-editing quality is not inferior to human translation. Furthermore, a statistical analysis found that editing volume does not correlate closely with productivity. This analysis implies that editing volume is one of the core factors that can explain productivity, but there can be other factors. In addition, a text analysis found that the frequency and severity of errors in raw machine translation are directly related to productivity losses. This paper discusses the reasons behind these findings and suggests how the industry and academia should use these findings.

키워드