Abstract
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation. We study gender biases associated with the protagonist in model-generated stories. Such biases may be expressed either explicitly ("women can't park") or implicitly (e.g. an unsolicited male character guides her into a parking space). We focus on implicit biases, and use a commonsense reasoning engine to uncover them. Specifically, we infer and analyze the protagonist's motivations, attributes, mental states, and implications on others. Our findings regarding implicit biases are in line with prior work that studied explicit biases, for example showing that female characters' portrayal is centered around appearance, while male figures' focus on intellect.
Original language | English |
---|---|
Title of host publication | Findings of the Association for Computational Linguistics, Findings of ACL |
Subtitle of host publication | EMNLP 2021 |
Editors | Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-Tau Yih |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 3866-3873 |
Number of pages | 8 |
ISBN (Electronic) | 9781955917100 |
State | Published - 2021 |
Externally published | Yes |
Event | 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 - Punta Cana, Dominican Republic Duration: 7 Nov 2021 → 11 Nov 2021 |
Publication series
Name | Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 |
---|
Conference
Conference | 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021 |
---|---|
Country/Territory | Dominican Republic |
City | Punta Cana |
Period | 7/11/21 → 11/11/21 |
Bibliographical note
Publisher Copyright:© 2021 Association for Computational Linguistics.