Screening Gender Transfer in Neural Machine Translation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Screening Gender Transfer in Neural Machine Translation

Abstract

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
Origin Publisher files allowed on an open archive

Dates and versions

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

Identifiers

  • HAL Id : hal-03424174 , version 1

Cite

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⟩
110 View
88 Download

Share

Gmail Mastodon Facebook X LinkedIn More