English

The presented study investigates the impact of automatic speech recognition (ASR) and assisting scripts on effort during transcription and translation processes, two main subprocesses of interlingual subtitling. Applying keylogging and eye tracking, this study takes a first look at how the integration of ASR impacts these subprocesses. 12 professional subtitlers and 13 translation students were recorded performing two intralingual transcriptions and three translation tasks to evaluate the impact on temporal, technical, and cognitive effort, and split-attention. Measures include editing time, visit count and duration, insertions, and deletions. The main findings show that, in both tasks, ASR did not significantly impact task duration, but participants had fewer keystrokes, indicating less technical effort. Regarding visual attention the existence of an ASR script did not decrease the time spent replaying the video. The study also shows that students were less efficient in their typin...

There has been noticeable growth in the use of intralingual and interlingual subtitling due to technological advances and accessibility legislation. The process of subtitling, however, has yet to be thoroughly investigated with empirical methods. Given that subtitling is a complex task, interpreting keylogging and eyetracking data in the overall process can be complicated. We therefore focus on the subprocesses involved in subtitling, i.e. transcription and translation of movie dialogue. With advancements in neural machine translation (NMT) especially with creative texts (Toral et al. 2018), research in this special field of translation becomes even more essential to find meaningful ways of improving subtitling processes and informing subtitling training. This development is focus of CompAsS (Computer-Assisted Subtitling), a project funded by the EU and managed by ZDF Digital and University of Mainz with the aim to improve current subtitling pro-

Language technologies, such as machine translation (MT), but also the application of artificial intelligence in general and an abundance of CAT tools and platforms have an increasing influence on the translation market. Human interaction with these technologies becomes ever more important as they impact translators’ workflows, work environments, and job profiles. Moreover, it has implications for translator training. One of the tasks that emerged with language technologies is post-editing (PE) where a human translator corrects raw machine translated output according to given guidelines and quality criteria (O’Brien, 2011: 197-198). Already widely used in several traditional translation settings, its use has come into focus in more creative processes such as literary translation and audiovisual translation (AVT) as well. With the integration of MT systems, the translation process should become more efficient. Both economic and cognitive processes are impacted and with it the necessar...

This paper presents results from a small pilot study carried out within the EU-funded Compass project. With eye tracking, subtitlers' distribution of attention and monitoring during subtitling with the commercial subtitling software FAB Subtitler was investigated and analysed. During three intralingual subtitling tasks for excerpts of German documentaries we recorded data on gaze activity of eight subtitlers. An annotation of the created subtitles based on a comparison of the subtitles from the recording and the corrected subtitles after post-experiment proofread-<br> ing allows us to link product with process data. We found that during subtitling, attention is shifted back and forth between monitoring the content of the evolving subtitles and the timing and segmentation thereof. Results show that subtitle reading times were longer on subtitles that were corrected during post-experiment proofreading. In addition, we found a significant interaction with subtitle ID in that ...