Screening Gender Transfer in Neural Machine Translation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 36 references that are in the map. First posted on arXiv 25 Feb 2022.
Builds on
20 of 36 references.
References · 20
- 2017Attention Is All You Needcited by 59,932
- 2016Understanding intermediate layers using linear classifier probescited by 1,279
- 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
- 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
- 2019Designing and Interpreting Probes with Control Taskscited by 608
- 2018Gender Bias in Coreference Resolutioncited by 438
- 2018Analysis Methods in Neural Language Processing: A Surveycited by 276
- 2019Evaluating Gender Bias in Machine Translationcited by 247
- 2019Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphologycited by 200
- 2018Assessing Gender Bias in Machine Translation -- A Case Study with Google Translatecited by 121
- 2021Gender Bias in Machine Translationcited by 116
- 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 102
8 more
- 2020Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problemcited by 86
- 2019Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniquescited by 65
- 2019Joey NMT: A Minimalist NMT Toolkit for Novicescited by 39
- 2019On the Linguistic Representational Power of Neural Machine Translation Modelscited by 34
- 2020Automatically Identifying Gender Issues in Machine Translation using Perturbationscited by 28
- 2021Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translationcited by 28
- 2021Investigating Failures of Automatic Translation in the Case of Unambiguous Gendercited by 20
- 2020Gender Bias in Multilingual Neural Machine Translation: The Architecture Matterscited by 11
Built on by
Citing papers per year: 2025: 1.
1 paper.