@inproceedings{lauscher-glavas-2019-consistently,
title = "Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors",
author = "Lauscher, Anne and
Glava{\v{s}}, Goran",
editor = "Mihalcea, Rada and
Shutova, Ekaterina and
Ku, Lun-Wei and
Evang, Kilian and
Poria, Soujanya",
booktitle = "Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*{SEM} 2019)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-1010",
doi = "10.18653/v1/S19-1010",
pages = "85--91",
abstract = "Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant dimensions like embedding models, types of texts, and different languages. In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models. Furthermore, we analyze the cross-lingual biases encoded in bilingual embedding spaces, indicative of the effects of bias transfer encompassed in cross-lingual transfer of NLP models. Our study yields some unexpected findings, e.g., that biases can be emphasized or downplayed by different embedding models or that user-generated content may be less biased than encyclopedic text. We hope our work catalyzes bias research in NLP and informs the development of bias reduction techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lauscher-glavas-2019-consistently">
<titleInfo>
<title>Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Lauscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilian</namePart>
<namePart type="family">Evang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant dimensions like embedding models, types of texts, and different languages. In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models. Furthermore, we analyze the cross-lingual biases encoded in bilingual embedding spaces, indicative of the effects of bias transfer encompassed in cross-lingual transfer of NLP models. Our study yields some unexpected findings, e.g., that biases can be emphasized or downplayed by different embedding models or that user-generated content may be less biased than encyclopedic text. We hope our work catalyzes bias research in NLP and informs the development of bias reduction techniques.</abstract>
<identifier type="citekey">lauscher-glavas-2019-consistently</identifier>
<identifier type="doi">10.18653/v1/S19-1010</identifier>
<location>
<url>https://aclanthology.org/S19-1010</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>85</start>
<end>91</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors
%A Lauscher, Anne
%A Glavaš, Goran
%Y Mihalcea, Rada
%Y Shutova, Ekaterina
%Y Ku, Lun-Wei
%Y Evang, Kilian
%Y Poria, Soujanya
%S Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F lauscher-glavas-2019-consistently
%X Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant dimensions like embedding models, types of texts, and different languages. In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models. Furthermore, we analyze the cross-lingual biases encoded in bilingual embedding spaces, indicative of the effects of bias transfer encompassed in cross-lingual transfer of NLP models. Our study yields some unexpected findings, e.g., that biases can be emphasized or downplayed by different embedding models or that user-generated content may be less biased than encyclopedic text. We hope our work catalyzes bias research in NLP and informs the development of bias reduction techniques.
%R 10.18653/v1/S19-1010
%U https://aclanthology.org/S19-1010
%U https://doi.org/10.18653/v1/S19-1010
%P 85-91
Markdown (Informal)
[Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors](https://aclanthology.org/S19-1010) (Lauscher & Glavaš, *SEM 2019)
ACL