Automatically Inferring Gender Associations from Language
This work addresses the problem of understanding gender biases in language for researchers and practitioners in NLP and social sciences, though it is incremental as it builds on existing methods with new datasets and integration.
The paper tackled the problem of automatically inferring gender associations from language by introducing two datasets and a novel integration of approaches, demonstrating large-scale differences in how people talk about women and men across domains, with human evaluations showing significant outperformance over strong baselines.
In this paper, we pose the question: do people talk about women and men in different ways? We introduce two datasets and a novel integration of approaches for automatically inferring gender associations from language, discovering coherent word clusters, and labeling the clusters for the semantic concepts they represent. The datasets allow us to compare how people write about women and men in two different settings - one set draws from celebrity news and the other from student reviews of computer science professors. We demonstrate that there are large-scale differences in the ways that people talk about women and men and that these differences vary across domains. Human evaluations show that our methods significantly outperform strong baselines.