Description du projet
La collaboration entre l’homme et la machine transforme la traduction littéraire
La traduction automatique correspond à l’application d’un logiciel automatisé basé sur l’IA pour traduire une langue parlée ou écrite. La rapidité est l’un des principaux avantages quand il s’agit de traduire des textes commerciaux et techniques. Mais qu’en est-il de la littérature? Elle constitue un défi en raison des aspects culturels et linguistiques qui entrent en jeu. C’est dans ce contexte, le projet DUAL-T, financé par l’UE, invitera des traducteurs littéraires professionnels à codévelopper une approche centrée sur l’utilisateur et à ouvrir la voie à des technologies de traduction littéraire améliorées et innovantes. Il incorporera de manière proactive la contribution des traducteurs littéraires afin de créer un nouveau flux de travail intégrant la technologie, en utilisant des entretiens, en testant les processus des traducteurs et en assurant une médiation entre les développeurs de technologies de traduction littéraire et les traducteurs littéraires. Les travaux du projet transformeront de manière significative les approches des interactions homme-machine dans la traduction littéraire.
Objectif
Recent years have seen a growing research interest on the application of translation technology to literary translation workflows, mostly in the form of Machine Translation (MT) or post-editing of MT output. In these studies, literary translators' voices are virtually absent. This project will address the discrepancy between research in Computer Science/AI and Translation Studies, as well as the absence of literary translators from the conversation surrounding technological innovation in their profession. It will do so by proactively integrating literary translators' input in the co-creation of a new technology-inclusive workflow. Professional literary translators will be asked to perform literary translation tasks using (1) MT + post-editing, (2) a Computer-Aided Translation (CAT) tool environment, (3) a CAT tool environment with integrated MT. User testing will be performed using eye tracking, keystroke logging and screen capturing. In-depth interviews and focus groups will be conducted before and after the translation task to register changes in participants' attitudes towards technology before and after using it, as well as advantages and pain points of the tool employed. Being the first study of this kind in literary translation, results will help to (1) devise a technology-inclusive literary translation workflow employing a user-led approach, (2) assess whether and to what extent translation technology can enhance literary translators (particularly, the potential of CAT tools to work in combination with MT and/or as an alternative to MT-centric approaches will be assessed), and (3) mediate a dialogue between literary translators and translation technology developers by feeding back data on literary translators' use of and attitudes towards translation technology to the project's industry partner. It is expected that the project's findings will also contribute to the wider conversation around Human-Computer Interaction in other professions.
Champ scientifique
Mots‑clés
Programme(s)
- HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA) Main Programme
Régime de financement
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European FellowshipsCoordinateur
9000 Gent
Belgique