Generating Clues for Gender based Occupation De-biasing in Text

TL;DR

This paper introduces a system that detects gender stereotypes related to occupations in text and provides counter-evidence to aid in de-biasing, supporting both AI training and human storytelling.

Contribution

It is the first system to identify gender stereotypes in occupation-related text and offer counter-evidence for de-biasing within specific geographical and temporal contexts.

Findings

System can detect gender stereotypes in occupation-related text.

Provides counter-evidence to challenge stereotypes.

Supports human-in-the-loop de-biasing process.

Abstract

Vast availability of text data has enabled widespread training and use of AI systems that not only learn and predict attributes from the text but also generate text automatically. However, these AI models also learn gender, racial and ethnic biases present in the training data. In this paper, we present the first system that discovers the possibility that a given text portrays a gender stereotype associated with an occupation. If the possibility exists, the system offers counter-evidences of opposite gender also being associated with the same occupation in the context of user-provided geography and timespan. The system thus enables text de-biasing by assisting a human-in-the-loop. The system can not only act as a text pre-processor before training any AI model but also help human story writers write stories free of occupation-level gender bias in the geographical and temporal context of their choice.