Post-editing neural machine translation versus translation memory segments
Sánchez-Gijón, Pilar (Universitat Autònoma de Barcelona)
Moorkens, Joss (Dublin City University)
Way, Andy (Dublin City University)

Data:	2019
Resum:	The use of neural machine translation (NMT) in a professional scenario implies a number of challenges despite growing evidence that, in language combinations such as English to Spanish, NMT output quality has already outperformed statistical machine translation in terms of automatic metric scores. This article presents the result of an empirical test that aims to shed light on the differences between NMT postediting and translation with the aid of a translation memory (TM). The results show that NMT postediting involves less editing than TM segments, but this editing appears to take more time, with the consequence that NMT post-editing does not seem to improve productivity as may have been expected. This might be due to the fact that NMT segments show a higher variability in terms of quality and time invested in post-editing than TM segments that are 'more similar' on average. Finally, results show that translators who perceive that NMT boosts their productivity actually performed faster than those who perceive that NMT slows them down.
Drets:	Tots els drets reservats.
Llengua:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Matèria:	Neural machine translation ; Translation memory ; Translation quality perception ; MT acceptance ; Translation productivity
Publicat a:	Machine translation, 2019, p. 1-29, ISSN 0922-6567

DOI: 10.1007/s10590-019-09232-x

Post-print 74 p, 7.7 MB

El registre apareix a les col·leccions:
Documents de recerca > Documents dels grups de recerca de la UAB > Centres i grups de recerca (producció científica) > Arts i humanitats > Grup de recerca Tradumàtica
Articles > Articles de recerca
Articles > Articles publicats