Mitigating Gender Bias in Natural Language Processing: Literature Review

2019/06/21 by Tony Sun, Andrew Gaut, Sun, Tony +17 · 46 citations
Computer Science · Social Sciences · #Ethics and Social Impacts of AI #Hate Speech and Cyberbullying Detection #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.1906.08976

Accepted to ACL 2019

arxiv created 2019/06/21 · arxiv updated 2019/06/24

Abstract

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in modeling various applications, they propagate and may even amplify gender bias found in text corpora. While the study of bias in artificial intelligence is not new, methods to mitigate gender bias in NLP are relatively nascent. In this paper, we review contemporary studies on recognizing and mitigating gender bias in NLP. We discuss gender bias based on four forms of representation bias and analyze methods recognizing gender bias. Furthermore, we discuss the advantages and drawbacks of existing gender debiasing methods. Finally, we discuss future studies for recognizing and mitigating gender bias in NLP.

Citations

• Equality of Opportunity in Supervised Learning
• On Fairness and Calibration

Cited by

• LoRA for Gender-Inclusive Rewriting and Activation Steering for Counter-Narrative Generation
• Us-vs-Them bias in Large Language Models
• Gender Bias in Emotion Recognition by Large Language Models
• ClinStructor: AI-Powered Structuring of Unstructured Clinical Texts
• Mitigating Gender Bias in Captioning Systems
• LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis
• Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
• Controlling Gender Bias in Retrieval via a Backpack Architecture
• Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models
• Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI
• An infographic framework of GeoAI ethics based on news data
• Context-aware Fairness Evaluation and Mitigation in LLMs
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Gender Bias in English-to-Greek Machine Translation
• A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts
• Augmenting Human-Centered Racial Covenant Detection and Georeferencing with Plug-and-Play NLP Pipelines
• Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations
• MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline
• Integrating gender inclusivity into large language models via instruction tuning
• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• Theories of "Sexuality" in Natural Language Processing Bias Research
• Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
• Gender-Neutral Machine Translation Strategies in Practice
• Overview of the NLPCC 2025 Shared Task: Gender Bias Mitigation Challenge
• AdvSumm: Adversarial Training for Bias Mitigation in Text Summarization
• BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
• taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades
• Intersectional Bias in Causal Language Models
• Visualization for interactively adjusting the de-bias effect of word embedding
• Different Speech Translation Models Encode and Translate Speaker Gender Differently
• GeNRe: A French Gender-Neutral Rewriting System Using Collective Nouns
• Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
• Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries
• The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability
• Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
• A Survey on Stereotype Detection in Natural Language Processing
• Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
• Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs
• Social Bias in Popular Question-Answering Benchmarks
• Inter(sectional) Alia(s): Ambiguity in Voice Agent Identity via Intersectional Japanese Self-Referents
• MT-Adapted Datasheets for Datasets: Template and Repository
• Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation
• Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures
• "Are we writing an advice column for Spock here?" Understanding Stereotypes in AI Advice for Autistic Users
• A closer look at how large language models trust humans: patterns and biases
• Fairness in Machine Learning-based Hand Load Estimation: A Case Study on Load Carriage Tasks

Related

• A Survey on Gender Bias in Natural Language Processing
• Gender Bias in Neural Natural Language Processing
• Theories of “Gender” in NLP Bias Research
• Theories of "Gender" in NLP Bias Research
• Identifying and Reducing Gender Bias in Word-Level Language Models