The Harm in Hate Speech

By Richard Delgado. 2013

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

In Safety, Robustness & Interpretability

Citations in the corpus

Refining Language Models with Compositional Explanations (2021, background): “With recent advances in model architectures and pre-training techniques, neural language models [4, 31, 25] have achieved impressive results on a broad set of natural language processing (NLP) tasks, such as sentiment analysis and hate speech detection [3, 45].”
Kaleidoscopic Justice: Sexual Violence and Victim-Survivors’ Perceptions of Justice (2019, methodology): “Rather, we are using it as a ‘value or principle embedded in a political argument’ (Waldron, 2012: 138), emphasizing that justice for victim-survivors is not just following the rules (though that is obviously essential).”
Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective (2020, background): “Online abusive content detection brings forward two conflicting human values: freedom of speech and respect for equality and dignity (Maitra & McGowan, 2012; Waldron, 2012; Gagliardone, Gal, Alves, & Martinez, 2015).”
Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation (2019, background): “This phenomena has been monitored, tracked, measured or quantiﬁed in a number of occasions [14, 15, 11].”
Contextualizing Hate Speech Classifiers with Post-hoc Explanation (2020, background): “Hate speech detection is part of the ongoing effort to limit the harm done by oppressive and abusive language (Waldron, 2012; Gelber and McNamara, 2016; Gagliardone et al., 2015; Mohan et al., 2017).”