"Unsex me here": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples

By Mattia Samory, Indira Sen, Julian Kohne, Fabian Flöck, Claudia Wagner. 2020

10 citations recorded by the source corpus.

Subfields: 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 Natural Language Processing

1. Bertie Vidgen
2. Douwe Kiela
3. Tristan Thrush
4. Zeerak Talat
5. Helen Z. Margetts
6. Dong Nguyen
7. Paul Röttger
8. Janet B. Pierrehumbert

In Safety, Robustness & Interpretability

1. Bertie Vidgen
2. Douwe Kiela
3. Tristan Thrush
4. Zeerak Talat
5. Paul Röttger
6. Helen Z. Margetts
7. Dong Nguyen
8. Isar Nejadgholi

Citations in the corpus

• HateCheck: Functional Tests for Hate Speech Detection Models (2020, background): “Corre-spondingly, models trained on such datasets have been shown to be overly sensitive to lexical features such as group identifiers (Park et al., 2018; Dixon et al., 2018; Kennedy et al., 2020), and to generalise poorly to other datasets (Nejadgholi and Kiritchenko, 2020; Samory et al., 2020).”
• Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection (2021, background): “Samory et al. (2020) create 2, 000 ‘hard-to-classify’ not-sexist examples which contrast sexist examples in their dataset.”