To Prefer or to Choose? Generating Agency and Power Counterfactuals Jointly for Gender Bias Mitigation

authored by

Maja Stahl, Maximilian Spliethöver, Henning Wachsmuth

Abstract

Gender bias may emerge from an unequal representation of agency and power, for example, by portraying women frequently as passive and powerless (“She accepted her future”) and men as proactive and powerful (“He chose his future”). When language models learn from respective texts, they may reproduce or even amplify the bias. An effective way to mitigate bias is to generate counterfactual sentences with opposite agency and power to the training. Recent work targeted agency-specific verbs from a lexicon to this end. We argue that this is insufficient, due to the interaction of agency and power and their dependence on context. In this paper, we thus develop a new rewriting model that identifies verbs with the desired agency and power in the context of the given sentence. The verbs’ probability is then boosted to encourage the model to rewrite both connotations jointly. According to automatic metrics, our model effectively controls for power while being competitive in agency to the state of the art. In our main evaluation, human annotators favored its counterfactuals in terms of both connotations, also deeming its meaning preservation better.

Organisation(s)

Natural Language Processing Section
Institute of Artificial Intelligence

Type

Conference contribution

Pages

39-51

No. of pages

13

Publication date

11.2022

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

Computer Science (miscellaneous), General Social Sciences

Sustainable Development Goals

SDG 5 - Gender Equality, SDG 10 - Reduced Inequalities

Electronic version(s)

https://aclanthology.org/2022.nlpcss-1.6/ (Access: Closed)