A general framework for implicit and explicit debiasing of distributional word vector spaces


Lauscher, Anne ; Glavaš, Goran ; Ponzetto, Simone Paolo ; Vulic, Ivan



URL: https://arxiv.org/pdf/1909.06092.pdf
Additional URL: https://arxiv.org/abs/1909.06092
Document Type: Working paper
Year of publication: 2019
Place of publication: Ithaca, NY
Publishing house: Cornell University
Publication language: English
Institution: School of Business Informatics and Mathematics > Text Analytics for Interdisciplinary Research (Juniorprofessur) (Glavaš 2017-)
School of Business Informatics and Mathematics > Wirtschaftsinformatik III (Ponzetto 2016-)
Subject: 004 Computer science, internet
Abstract: Distributional word vectors have recently been shown to encode many of the human biases, most notably gender and racial biases, and models for attenuating such biases have consequently been proposed. However, existing models and studies (1) operate on under-specified and mutually differing bias definitions, (2) are tailored for a particular bias (e.g., gender bias) and (3) have been evaluated inconsistently and non-rigorously. In this work, we introduce a general framework for debiasing word embeddings. We operationalize the definition of a bias by discerning two types of bias specification: explicit and implicit. We then propose three debiasing models that operate on explicit or implicit bias specifications, and that can be composed towards more robust debiasing. Finally, we devise a full-fledged evaluation framework in which we couple existing bias metrics with newly proposed ones. Experimental findings across three embedding methods suggest that the proposed debiasing models are robust and widely applicable: they often completely remove the bias both implicitly and explicitly, without degradation of semantic information encoded in any of the input distributional spaces. Moreover, we successfully transfer debiasing models, by means of cross-lingual embedding spaces, and remove or attenuate biases in distributional word vector spaces of languages that lack readily available bias specifications.

Dieser Eintrag ist Teil der Universitätsbibliographie.




+ Citation Example and Export

Lauscher, Anne ; Glavaš, Goran ; Ponzetto, Simone Paolo ; Vulic, Ivan (2019) A general framework for implicit and explicit debiasing of distributional word vector spaces. Ithaca, NY [Working paper]


+ Search Authors in

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item