Skip to Main content Skip to Navigation
Conference papers

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.
Document type :
Conference papers
Complete list of metadata
Contributor : François Yvon Connect in order to contact the contributor
Submitted on : Wednesday, November 10, 2021 - 1:02:07 PM
Last modification on : Monday, May 2, 2022 - 1:58:04 PM
Long-term archiving on: : Friday, February 11, 2022 - 6:50:15 PM


Publisher files allowed on an open archive


  • HAL Id : hal-03424174, version 1


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⟩



Record views


Files downloads