DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces

Niklas Friedrich, Anne Lauscher, Simone Paolo Ponzetto, Goran Glavaš


Abstract
Recent research efforts in NLP have demonstrated that distributional word vector spaces often encode stereotypical human biases, such as racism and sexism. With word representations ubiquitously used in NLP models and pipelines, this raises ethical issues and jeopardizes the fairness of language technologies. While there exists a large body of work on bias measures and debiasing methods, to date, there is no platform that would unify these research efforts and make bias measuring and debiasing of representation spaces widely accessible. In this work, we present DebIE, the first integrated platform for (1) measuring and (2) mitigating bias in word embeddings. Given an (i) embedding space (users can choose between the predefined spaces or upload their own) and (ii) a bias specification (users can choose between existing bias specifications or create their own), DebIE can (1) compute several measures of implicit and explicit bias and modify the embedding space by executing two (mutually composable) debiasing models. DebIE’s functionality can be accessed through four different interfaces: (a) a web application, (b) a desktop application, (c) a REST-ful API, and (d) as a command-line application. DebIE is available at: debie.informatik.uni-mannheim.de.
Anthology ID:
2021.eacl-demos.11
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
Month:
April
Year:
2021
Address:
Online
Editors:
Dimitra Gkatzia, Djamé Seddah
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
91–98
Language:
URL:
https://aclanthology.org/2021.eacl-demos.11
DOI:
10.18653/v1/2021.eacl-demos.11
Bibkey:
Cite (ACL):
Niklas Friedrich, Anne Lauscher, Simone Paolo Ponzetto, and Goran Glavaš. 2021. DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 91–98, Online. Association for Computational Linguistics.
Cite (Informal):
DebIE: A Platform for Implicit and Explicit Debiasing of Word Embedding Spaces (Friedrich et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-demos.11.pdf
Code
 nfriedri/debie-backend +  additional community code