Screening Gender Transfer in Neural Machine Translation - Traitement du Langage Parlé Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Screening Gender Transfer in Neural Machine Translation

Résumé

This paper aims at identifying the information flow in state-of-the-art machine translation systems, taking as example the transfer of gender when translating from French into English. Using a controlled set of examples, we experiment several ways to investigate how gender information circulates in a encoder-decoder architecture considering both probing techniques as well as interventions on the internal representations used in the MT system. Our results show that gender information can be found in all token representations built by the encoder and the decoder and lead us to conclude that there are multiple pathways for gender transfer.
Fichier principal
Vignette du fichier
2021.blackboxnlp-1.24.pdf (329.88 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03424174 , version 1 (10-11-2021)

Identifiants

  • HAL Id : hal-03424174 , version 1

Citer

Guillaume Wisniewski, Lichao Zhu, Nicolas Ballier, François Yvon. Screening Gender Transfer in Neural Machine Translation. Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Association for computational linguistics, Nov 2021, Punta Cana, Dominica. ⟨hal-03424174⟩
104 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More