Article | Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland | Gender Bias in Pretrained Swedish Embeddings Linköping University Electronic Press Conference Proceedings
Göm menyn

Title:
Gender Bias in Pretrained Swedish Embeddings
Author:
Magnus Sahlgren: RISE, Sweden Fredrik Olsson: RISE, Sweden
Download:
Full text (pdf)
Year:
2019
Conference:
Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland
Issue:
167
Article no.:
004
Pages:
35--43
No. of pages:
8
Publication type:
Abstract and Fulltext
Published:
2019-10-02
ISBN:
978-91-7929-995-8
Series:
Linköping Electronic Conference Proceedings
ISSN (print):
1650-3686
ISSN (online):
1650-3740
Series:
NEALT Proceedings Series
Publisher:
Linköping University Electronic Press, Linköpings universitet


Export in BibTex, RIS or text

This paper investigates the presence of gender bias in pretrained Swedish embeddings. We focus on a scenario where names are matched with occupations, and we demonstrate how a number of standard pretrained embeddings handle this task. Our experiments show some significant differences between the pretrained embeddings, with word-based methods showing the most bias and contextualized language models showing the least. We also demonstrate that the previously proposed debiasing method does not affect the performance of the various embeddings in this scenario.

Keywords: gender bias word embeddings contextualized embeddings pretrained Swedish embeddings

Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

Author:
Magnus Sahlgren, Fredrik Olsson
Title:
Gender Bias in Pretrained Swedish Embeddings
References:
No references available

Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

Author:
Magnus Sahlgren, Fredrik Olsson
Title:
Gender Bias in Pretrained Swedish Embeddings
Note: the following are taken directly from CrossRef
Citations:
No citations available at the moment


Responsible for this page: Peter Berkesand
Last updated: 2019-11-06