Exploring Gender Bias Beyond Occupational Titles
This work addresses gender bias in AI for NLP applications, but it is incremental as it builds on existing bias detection methods with a new dataset.
The researchers tackled the problem of gender bias in language beyond occupational stereotypes by introducing a new dataset and framework, achieving improved explainability and confirming biases in diverse datasets including Japanese.
In this work, we investigate the correlation between gender and contextual biases, focusing on elements such as action verbs, object nouns, and particularly on occupations. We introduce a novel dataset, GenderLexicon, and a framework that can estimate contextual bias and its related gender bias. Our model can interpret the bias with a score and thus improve the explainability of gender bias. Also, our findings confirm the existence of gender biases beyond occupational stereotypes. To validate our approach and demonstrate its effectiveness, we conduct evaluations on five diverse datasets, including a Japanese dataset.