Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10457041" target="_blank" >RIV/00216208:11320/22:10457041 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.gebnlp-1.3.pdf" target="_blank" >https://aclanthology.org/2022.gebnlp-1.3.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information
Original language description
The representations in large language models contain multiple types of gender information. We focus on two types of such signals in English texts: factual gender information, which is a grammatical or semantic property, and gender bias, which is the correlation between a word and specific gender. We can disentangle the model’s embeddings and identify components encoding both types of information with probing. We aim to diminish the stereotypical bias in the representations while preserving the factual gender signal. Our filtering method shows that it is possible to decrease the bias of gender-neutral profession names without significant deterioration of language modeling capabilities. The findings can be applied to language generation to mitigate reliance on stereotypes while preserving gender agreement in coreferences.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
ISBN
978-1-955917-68-1
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
17-29
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Seattle, WA, USA
Event date
Sep 15, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—