CAT Tools Usability Test with Eye-Tracking and Key-Logging: Where Translation Studies Meets Natural Language Processing

Abstract

Computer assisted tools used to seem as though not made from the point of view of their targeted users [O’Brien, 2012:15]. However, their usability has been improving. In Translation Studies there exists a gap in research on process-oriented usability involving data triangulation. In our study based on the assumption that translation is a situated and complex activity [Risku, 2002, 2004], we aimed to address this gap with our experiment testing a new tool for translators, Concordia. This usability experiment with eye-tracking, keylogging, and screen recording directly involved translators (six translation trainees) in the development process through objectively collected data on effectiveness and efficiency of Concordia. Their satisfaction with Concordia was also a part of the usability test. We hypothesised that participants would be more efficient and effective when translating European Union texts with Concordia and that they will be satisfied with the tool. The results indicate that Concordia at its current state of development does not facilitate the process, but the participants were generally satisfied with the tool’s features.