Mitigating Gender Bias in Natural Language Processing: Literature Review

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.

arXiv commentAccepted to ACL 2019

References in corpus (14)

• Semantics derived automatically from language corpora contain human-like biases
• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• On Fairness and Calibration
• The Frontiers of Fairness in Machine Learning
• Fairness Without Demographics in Repeated Loss Minimization
• Getting Gender Right in Neural Machine Translation
• Women also Snowboard: Overcoming Bias in Captioning Models
• A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing
• Gender Bias in Neural Natural Language Processing
• Gender Bias in Contextualized Word Embeddings
• Tie-breaker: Using language models to quantify gender bias in sports journalism

Cited by in corpus (16)

• Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
• Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
• Pre-trained Language Models in Biomedical Domain: A Systematic Survey
• Intersectional Bias in Causal Language Models
• MT-Adapted Datasheets for Datasets: Template and Repository
• Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
• Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Computer Science Communities: Who is Speaking, and Who is Listening to the Women? Using an Ethics of Care to Promote Diverse Voices
• Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification
• The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability
• MDR Cluster-Debias: A Nonlinear WordEmbedding Debiasing Pipeline
• Mitigating Gender Bias in Captioning Systems
• Interactive Storytelling for Children: A Case-study of Design and Development Considerations for Ethical Conversational AI
• Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
• OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings