How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification

Kurzanzeige
dc.contributor.authorTokpo, Ewoenam Kwaku
dc.contributor.authorDelobelle, Pieter
dc.contributor.authorBerendt, Bettina
dc.contributor.authorCalders, Toon
dc.date.accessioned2024-05-02T15:03:16Z
dc.date.available2024-05-02T15:03:16Z
dc.date.issued2023
dc.description.abstractTo mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classification, it is important to understand how these intrinsic bias mitigation strategies actually translate to fairness in downstream tasks and the extent of this. In this work, we design a probe to investigate the effects that some of the major intrinsic gender bias mitigation strategies have on downstream text classification tasks. We discover that instead of resolving gender bias, intrinsic mitigation techniques and metrics are able to hide it in such a way that significant gender information is retained in the embeddings. Furthermore, we show that each mitigation technique is able to hide the bias from some of the intrinsic bias measures but not all, and each intrinsic bias measure can be fooled by some mitigation techniques, but not all. We confirm experimentally, that none of the intrinsic mitigation techniques used without any other fairness intervention is able to consistently impact extrinsic bias. We recommend that intrinsic bias mitigation techniques should be combined with other fairness interventions for downstream tasks.en
dc.identifier.citationTokpo, E. K., Delobelle, P., Berendt, B., & Calders, T. (2023). How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 3418–3433. https://doi.org/10.18653/v1/2023.eacl-main.248
dc.identifier.doihttps://doi.org/10.18653/v1/2023.eacl-main.248
dc.identifier.urihttps://www.weizenbaum-library.de/handle/id/631
dc.language.isoeng
dc.publisherAssociation for Computational Linguistics
dc.rightsopen access
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/3.0/
dc.subjectlanguage modelsen
dc.subjectbiasen
dc.subjectgender biasen
dc.titleHow Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification
dc.typeConferencePaper
dc.type.statuspublishedVersion
dcmi.typeText
dcterms.bibliographicCitation.urlhttps://doi.org/10.18653/v1/2023.eacl-main.248
local.researchgroupDaten, algorithmische Systeme und Ethik
local.researchtopicDigitale Technologien in der Gesellschaft
Dateien
Originalbündel
Gerade angezeigt 1 - 1 von 1
Vorschaubild
Name:
Tokpo-et-al_2023_How-Far-Can-It-Go.pdf
Größe:
888.89 KB
Format:
Adobe Portable Document Format
Beschreibung:
Herunterladen
Sammlungen
Digitale Technologien in der Gesellschaft