An analysis of gender bias studies in natural language processing

By Marta Ruiz Costa-jussà. 2019

68 citations recorded by the source corpus.

Subfields: Safety Research, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety Research

1. Marco Turchi
2. Marco Gaido
3. Beatrice Savoldi
4. Matteo Negri
5. Luisa Bentivogli
6. Christine Basta
7. Marta Ruiz Costa-jussà
8. Jason Aaron Edward Weston

In Natural Language Processing

1. Jason Aaron Edward Weston
2. Douwe Kiela
3. Adina Williams
4. Mohit Bansal
5. Emily Dinan
6. Kyunghyun Cho
7. Yonatan Belinkov
8. Yejin Choi

In Safety, Robustness & Interpretability

1. Adina Williams
2. Jason Aaron Edward Weston
3. Emily Dinan
4. Douwe Kiela
5. Eric Michael Smith
6. Marta Ruiz Costa-jussà
7. Christine Basta
8. Marco Turchi

Citations in the corpus

• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables (2020, background): “For example, the generated natural language could have certain biases, which have been reported in many natural language understanding systems [39, 40].”
• Multi-Dimensional Gender Bias Classification (2020, background): “Gender affects myriad aspects of NLP, including corpora, tasks, algorithms, and systems (Chang et al., 2019; Costa-jussà, 2019; Sun et al., 2019).”
• Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information (2020, background): “Gender bias is negatively affecting Natural Language Processing (NLP) (Costa-juss ` a, 2019; Sun et al., 2019).”
• Gender Bias in Machine Translation (2021, methodology): “We go beyond surveys restricted to monolingual NLP (Sun et al., 2019) or that are more limited in scope (Costa-jussà, 2019; Monti, 2020), and present the first comprehensive review of gender bias in MT.”