A Comparative Study of Human Translation and Machine Translation with Post-Editing

Abstract

With rapid advances in technology, many improvements have been made to make machine translation (MT) an effective tool for translators in the process of translation. However, an important issue that has not been extensively investigated is the use of automatic MT systems with postediting in comparison to human translation. The purpose of the present study, therefore, is to explore the similarities, differences, and processes of these two modes of translation. In terms of research methods, two groups of college students with different English proficiency levels were asked to translate a cell phone user guide written in English. In each group, some students received only the English source text while others received the source text in addition to a machine-translated Chinese text for postediting. Google Translate was the MT system used in this study because of its easy and free accessibility. A total of 140 subjects were timed on their translation tasks, and their performance was determined by the number of errors in the translated text. The statistical results indicated that the MT text was very helpful in reducing errors in some student translations; the use of MT also shortened the gap between students of divergent language proficiency levels. Further qualitative analysis elucidated how the MT text was utilized and the discrepancies in lexical choice and other aspects between the two groups of students. This back-end analysis of the machine translation process may offer insights into the practical use of human-assisted machine translation, as well as problems encountered by students when translating. It is hoped that these results may serve as a basis to facilitate future machine translation studies and teaching.