Do Neural Ranking Models Intensify Gender Bias?

Abstract

Concerns regarding the footprint of societal biases in information retrieval (IR) systems have been raised in several previous studies. In this work, we examine various recent IR models from the perspective of the degree of gender bias in their retrieval results. To this end, we first provide a bias measurement framework which includes two metrics to quantify the degree of the unbalanced presence of gender-related concepts in a given IR model's ranking list. To examine IR models by means of the framework, we create a dataset of non-gendered queries, selected by human annotators. Applying these queries to the MS MARCO Passage retrieval collection, we then measure the gender bias of a BM25 model and several recent neural ranking models. The results show that while all models are strongly biased toward male, the neural models, and in particular the ones based on contextualized embedding models, significantly intensify gender bias. Our experiments also show an overall increase in the gender bias of neural models when they exploit transfer learning, namely when they use (already biased) pre-trained embeddings.

In Proceedings of ACM SIGIR 2020

References in corpus (1)

• End-to-End Neural Ad-hoc Ranking with Kernel Pooling

Cited by in corpus (7)

• Societal Biases in Retrieved Contents: Measurement Framework and Adversarial Mitigation for BERT Rankers
• Unlearning Protected User Attributes in Recommendations with Adversarial Training
• Artificial Concepts of Artificial Intelligence: Institutional Compliance and Resistance in AI Startups
• Bias in Conversational Search: The Double-Edged Sword of the Personalized Knowledge Graph
• Much Ado About Gender: Current Practices and Future Recommendations for Appropriate Gender-Aware Information Access
• Predictive Uncertainty-based Bias Mitigation in Ranking
• Towards Fair Rankings: Leveraging LLMs for Gender Bias Detection and Measurement