Speech-Enabled Computer-Aided Translation: A Satisfaction Survey with Post-Editor Trainees

Abstract

The present study has surveyed post-editor trainees' views and attitudes before and after the introduction of speech technology as a front end to a computer-aided translation workbench. The aim of the survey was (i) to identify attitudes and perceptions among post-editor trainees before performing a post-editing task using automatic speech recognition (ASR); and (ii) to assess the degree to which post-editors' attitudes and expectations to the use of speech technology changed after actually using it. The survey was based on two questionnaires: the first one administered before the participants performed with the ASR system and the second one at the end of the session, once they have actually used ASR while post-editing machine translation outputs. Overall, the results suggest that the surveyed posteditor trainees tended to report a positive view of ASR in the context of post-editing and they would consider adopting ASR as an input method for future post-editing tasks.

Exploring multimodality for translator-computer interaction

“…This being said, over the past two decades, certain researchers, trainers and professionals have demonstrated an interest in using VR technology in translation [1,4,6,7,8,10,11,18,19,24,25]. However, none of today's off-the-shelf stand-alone VR systems was developed specifically for translation purposes.…”

“…One possible way to do this is by enabling multimodal interaction. In a recent study by MesaLao [19], student translators surveyed reported that they would welcome the integration of voice input as one of the possible input modes for performing translation tasks. Indeed, 80% of respondents stated that they would definitely consider adopting VR in combination with non-speech input modes in their daily work as translators.…”

MMPE: A Multi-Modal Interface for Post-Editing Machine Translation

“…A more recent approach, called SEECAT (Martinez et al, 2014), investigates the use of automatic speech recognition (ASR) in PE and argues that its combination with typing could boost productivity. A survey regarding speech usage with PE trainees (Mesa-Lao, 2014) finds that they have a positive attitude towards speech input and would consider adopting it, but only as a complement to other modalities. In a small-scale study, Zapata et al (2017) found that ASR for PE was faster than ASR for translation from scratch.…”

MMPE: A Multi-Modal Interface using Handwriting, Touch Reordering, and Speech Commands for Post-Editing Machine Translation

“…While most computer-aided translation (CAT) tools focus on traditional translation and incorporate only mouse & keyboard, previous research investigated other input modalities: automatic speech recognition (ASR) for dictating translations has already been explored in the 90s (Dymetman et al, 1994;Brousseau et al, 1995) and the more recent investigation of ASR for PE (Martinez et al, 2014) even argues that a combination with typing could boost productivity. Mesa-Lao (2014) finds that PE trainees have a positive attitude towards speech input and would consider adopting it, and Zapata et al (2017) found that ASR for PE was faster than ASR for translation from scratch. Due to these benefits, commercial CAT tools like memoQ and MateCat are also beginning to integrate ASR.…”