MT for Subtitling: Investigating professional translators' user experience and feedback

摘要

This paper presents a study of machine translation and post-editing in the field of audiovisual translation. We analyse user experience data collected from post-editing tasks completed by twelve translators in four language pairs. We also present feedback provided by the translators in semi-structured interviews. The results of the user experience survey and thematic analysis of interviews shows that the translators' impression of post-editing subtitles was on average neutral to somewhat negative, with segmentation and timing of subtitles identified as a key factor. Finally, we discuss the implications of the issues arising from the user experience survey and interviews for the future development of automatic subtitle translation.