A World Full of Stereotypes? Further Investigation on Origin and Gender Bias in Multi-Lingual Word Embeddings

Kurpicz-Briki, Mascha; Leoni, Tomaso Aurelio Domenico (2021). A World Full of Stereotypes? Further Investigation on Origin and Gender Bias in Multi-Lingual Word Embeddings Frontiers in Big Data, 4(625290) Frontiers 10.3389/fdata.2021.625290

Preview

Text fdata-04-625290.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (304kB) | Preview

Publicly available off-the-shelf word embeddings that are often used in productive applications for natural language processing have been proven to be biased. We have previously shown that this bias can come in a different form, depending on the language and the cultural context. In this work we extend our previous work and further investigate how bias varies in different languages. We examine Italian and Swedish word embeddings for gender and origin bias, and demonstrate how an origin bias concerning local migration groups in Switzerland is included in German word embeddings. We propose BiasWords, a method to automatically detect new forms of bias. Finally, we discuss how cultural and language aspects are relevant to the impact of bias on the application, and to potential mitigation measures.

Item Type:	Journal Article (Original Article)
Division/Institute:	School of Engineering and Computer Science > Institute for Data Applications and Security (IDAS) School of Engineering and Computer Science
Name:	Kurpicz-Briki, Maschahttps://orcid.org/0000-0001-5539-6370 and Leoni, Tomaso Aurelio Domenico
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
ISSN:	2624-909X
Publisher:	Frontiers
Language:	English
Submitter:	Mascha Kurpicz-Briki
Date Deposited:	18 Jun 2021 09:18
Last Modified:	24 Sep 2021 02:18
Publisher DOI:	10.3389/fdata.2021.625290
ARBOR DOI:	10.24451/arbor.14815
URI:	https://arbor.bfh.ch/id/eprint/14815