Thesis Distillation: Investigating The Impact of Bias in NLP Models on
Hate Speech Detection
- URL: http://arxiv.org/abs/2308.16549v2
- Date: Tue, 5 Dec 2023 11:43:44 GMT
- Title: Thesis Distillation: Investigating The Impact of Bias in NLP Models on
Hate Speech Detection
- Authors: Fatma Elsafoury
- Abstract summary: This paper is a summary of the work done in my PhD thesis.
I investigate the impact of bias in NLP models on the task of hate speech detection from three perspectives.
- Score: 6.2548734896918505
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation.
We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process.
We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
arXiv Detail & Related papers (2023-11-15T00:02:25Z) - Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research [75.84463664853125]
We provide a first attempt to quantify concerns regarding three topics, namely, environmental impact, equity, and impact on peer reviewing.
We capture existing (dis)parities between different and within groups with respect to seniority, academia, and industry.
We devise recommendations to mitigate found disparities, some of which already successfully implemented.
arXiv Detail & Related papers (2023-06-29T12:44:53Z) - On Bias and Fairness in NLP: Investigating the Impact of Bias and Debiasing in Language Models on the Fairness of Toxicity Detection [7.297345802761503]
representation bias, selection bias and overamplification bias are investigated.
We show that overamplification bias is the most impactful type of bias on the fairness of the task of toxicity detection.
We introduce a list of guidelines to ensure the fairness of the task of toxicity detection.
arXiv Detail & Related papers (2023-05-22T08:44:00Z) - On the Origins of Bias in NLP through the Lens of the Jim Code [1.256413718364189]
We trace the biases in current natural language processing (NLP) models back to their origins in racism, sexism, and homophobia over the last 500 years.
We show how the causes of the biases in the NLP pipeline are rooted in social issues.
arXiv Detail & Related papers (2023-05-16T08:37:13Z) - From Pretraining Data to Language Models to Downstream Tasks: Tracking
the Trails of Political Biases Leading to Unfair NLP Models [40.89699305385269]
Language models (LMs) are pretrained on diverse data sources, including news, discussion forums, books, and online encyclopedias.
We develop new methods to measure political biases in LMs trained on such corpora, along social and economic axes, and on top of politically biased LMs.
We focus on hate speech and misinformation detection, aiming to empirically quantify the effects of political (social, economic) biases in pretraining data on the fairness of high-stakes social-oriented tasks.
arXiv Detail & Related papers (2023-05-15T00:06:30Z) - SemEval-2023 Task 11: Learning With Disagreements (LeWiDi) [75.85548747729466]
We report on the second edition of the LeWiDi series of shared tasks.
This second edition attracted a wide array of participants resulting in 13 shared task submission papers.
arXiv Detail & Related papers (2023-04-28T12:20:35Z) - Fair Enough: Standardizing Evaluation and Model Selection for Fairness
Research in NLP [64.45845091719002]
Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct.
This paper seeks to clarify the current situation and plot a course for meaningful progress in fair learning.
arXiv Detail & Related papers (2023-02-11T14:54:00Z) - Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the
Research Manifold [88.83876819883653]
We show through a manual classification of recent NLP research papers that this is indeed the case.
We observe that NLP research often goes beyond the square one setup, focusing not only on accuracy, but also on fairness or interpretability, but typically only along a single dimension.
arXiv Detail & Related papers (2022-06-20T13:04:23Z) - A Survey on Bias and Fairness in Natural Language Processing [1.713291434132985]
We analyze the origins of biases, the definitions of fairness, and how different subfields of NLP bias can be mitigated.
We discuss how future studies can work towards eradicating pernicious biases from NLP algorithms.
arXiv Detail & Related papers (2022-03-06T18:12:30Z) - Sentiment Analysis Based on Deep Learning: A Comparative Study [69.09570726777817]
The study of public opinion can provide us with valuable information.
The efficiency and accuracy of sentiment analysis is being hindered by the challenges encountered in natural language processing.
This paper reviews the latest studies that have employed deep learning to solve sentiment analysis problems.
arXiv Detail & Related papers (2020-06-05T16:28:10Z) - Language (Technology) is Power: A Critical Survey of "Bias" in NLP [11.221552724154986]
We survey 146 papers analyzing "bias" in NLP systems.
We find that their motivations are vague, inconsistent, and lacking in normative reasoning.
We propose three recommendations that should guide work analyzing "bias" in NLP systems.
arXiv Detail & Related papers (2020-05-28T14:32:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.