Thesis Distillation: Investigating The Impact of Bias in NLP Models on Hate Speech Detection
Not on the map. Why?
Abstract (arXiv)
This paper is a summary of the work done in my PhD thesis. Where I investigate the impact of bias in NLP models on the task of hate speech detection from three perspectives: explainability, offensive stereotyping bias, and fairness. Then, I discuss the main takeaways from my thesis and how they can benefit the broader NLP community. Finally, I discuss important future research directions. The findings of my thesis suggest that the bias in NLP models impacts the task of hate speech detection from all three perspectives. And that unless we start incorporating social sciences in studying bias in NLP models, we will not effectively overcome the current limitations of measuring and mitigating bias in NLP models.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 67 references that are in the map. First posted on arXiv 31 Aug 2023.
Builds on
28 of 67 references.
References · 28
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
- 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
- 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
- 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
- 2019On Measuring Social Biases in Sentence Encoderscited by 397
- 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
- 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 346
- 2019Measuring Bias in Contextualized Word Representationscited by 275
- 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
16 more
- 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
- 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
- 2020Towards Debiasing Sentence Representationscited by 170
- 2020Intrinsic Bias Metrics Do Not Correlate with Application Biascited by 148
- 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
- 2019A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Mediacited by 95
- 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
- 2019Perturbation Sensitivity Analysis to Detect Unintended Model Biasescited by 74
- 2019Attenuating Bias in Word Vectorscited by 64
- 2022Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Taskscited by 48
- 2020Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Boardcited by 24
- 2022Explainable Abuse Detection as Intent Classification and Slot Fillingcited by 11
- 2023On the Origins of Bias in NLP through the Lens of the Jim Codecited by 5
- 2017Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionarycited by 3
- 20204chan & 8chan embeddingscited by 1
- 2023Systematic Offensive Stereotyping (SOS) Bias in Language Modelscited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.