Learning Advanced Post-editing

Abstract

This chapter reports the results of a longitudinal study (LS14) in which the CASMACAT post-editing workbench was tested with interactive translation prediction (ITP). Whereas previous studies with the CASMACAT workbench (Sanchis-Trilles et al., Machine Translation, 2014) or similar systems (Langlais et al., Machine Translation, 15, 77–98, 2004) tested user interaction only for a few days, the aim of this study was primarily to find out whether and how the performance of professional post-editors improved over time when working with the CASMACAT ITP feature. We were also interested in uncovering any specific profiles of translators depending on personal factors such as previous experience in post-editing and typing skills. Finally, the aim was also to collect feedback from the post-editors in order to know more about their views regarding this type of technology.