Screening Gender Transfer in Neural Machine Translation [article]

Guillaume Wisniewski, Lichao Zhu, Nicolas Ballier, François Yvon
2022 arXiv   pre-print
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
more » ... in all token representations built by the encoder and the decoder and lead us to conclude that there are multiple pathways for gender transfer.
arXiv:2202.12568v1 fatcat:j7eca73b3fgs5ems6ca6xuzoke