The MAKE-NMTViz Project: Meaningful, Accurate and Knowledge-limited Explanations of NMT Systems for Translators

Gabriela Gonzalez-Saez (1, 2) , Fabien Lopez (2, 1) , Mariam Nakhle (2, 1, 3) , Marco Dinarelli (2, 1) , Emmanuelle Esperança-Rodier (1) , Sui He (4) , Caroline Rossi (5) , Didier Schwab (2, 1) , Jun Yang (4) , James Robert Turner (4) , Nicolas Ballier (6, 7)

1 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
2 LIG - Laboratoire d'Informatique de Grenoble
3 Lingua Custodia
4 Swansea University
5 ILCEA4 - Institut des Langues et Cultures d'Europe, Amérique, Afrique, Asie et Australie
6 CLILLAC-ARP (URP_3967) - Centre de Linguistique Inter-langues, de Lexicologie, de Linguistique Anglaise et de Corpus
7 LLF - UMR7110 - Laboratoire de Linguistique Formelle

This paper describes MAKE-NMTViz, a project designed to help translators visualize neural machine translation outputs using explainable artificial intelligence visualization tools initially developed for computer vision.

Domains: Computer Science [cs]

Gabriela Gonzalez-Saez, Fabien Lopez, Mariam Nakhle, Marco Dinarelli, Emmanuelle Esperança-Rodier, et al.. The MAKE-NMTViz Project: Meaningful, Accurate and Knowledge-limited Explanations of NMT Systems for Translators. EAMT : European Association for Machine Translation, Jun 2024, Sheffield, United Kingdom. ⟨hal-04638945⟩