@inproceedings{devinney-etal-2023-developing,
title = "Developing a Multilingual Corpus of {W}ikipedia Biographies",
author = "Devinney, Hannah and
Eklund, Anton and
Ryazanov, Igor and
Cai, Jingwen",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.ranlp-1.32",
pages = "285--294",
abstract = "For many languages, Wikipedia is the most accessible source of biographical information. Studying how Wikipedia describes the lives of people can provide insights into societal biases, as well as cultural differences more generally. We present a method for extracting datasets of Wikipedia biographies. The accompanying codebase is adapted to English, Swedish, Russian, Chinese, and Farsi, and is extendable to other languages. We present an exploratory analysis of biographical topics and gendered patterns in four languages using topic modelling and embedding clustering. We find similarities across languages in the types of categories present, with the distribution of biographies concentrated in the language{'}s core regions. Masculine terms are over-represented and spread out over a wide variety of topics. Feminine terms are less frequent and linked to more constrained topics. Non-binary terms are nearly non-represented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="devinney-etal-2023-developing">
<titleInfo>
<title>Developing a Multilingual Corpus of Wikipedia Biographies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Devinney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Eklund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Ryazanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwen</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>For many languages, Wikipedia is the most accessible source of biographical information. Studying how Wikipedia describes the lives of people can provide insights into societal biases, as well as cultural differences more generally. We present a method for extracting datasets of Wikipedia biographies. The accompanying codebase is adapted to English, Swedish, Russian, Chinese, and Farsi, and is extendable to other languages. We present an exploratory analysis of biographical topics and gendered patterns in four languages using topic modelling and embedding clustering. We find similarities across languages in the types of categories present, with the distribution of biographies concentrated in the language’s core regions. Masculine terms are over-represented and spread out over a wide variety of topics. Feminine terms are less frequent and linked to more constrained topics. Non-binary terms are nearly non-represented.</abstract>
<identifier type="citekey">devinney-etal-2023-developing</identifier>
<location>
<url>https://aclanthology.org/2023.ranlp-1.32</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>285</start>
<end>294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing a Multilingual Corpus of Wikipedia Biographies
%A Devinney, Hannah
%A Eklund, Anton
%A Ryazanov, Igor
%A Cai, Jingwen
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F devinney-etal-2023-developing
%X For many languages, Wikipedia is the most accessible source of biographical information. Studying how Wikipedia describes the lives of people can provide insights into societal biases, as well as cultural differences more generally. We present a method for extracting datasets of Wikipedia biographies. The accompanying codebase is adapted to English, Swedish, Russian, Chinese, and Farsi, and is extendable to other languages. We present an exploratory analysis of biographical topics and gendered patterns in four languages using topic modelling and embedding clustering. We find similarities across languages in the types of categories present, with the distribution of biographies concentrated in the language’s core regions. Masculine terms are over-represented and spread out over a wide variety of topics. Feminine terms are less frequent and linked to more constrained topics. Non-binary terms are nearly non-represented.
%U https://aclanthology.org/2023.ranlp-1.32
%P 285-294
Markdown (Informal)
[Developing a Multilingual Corpus of Wikipedia Biographies](https://aclanthology.org/2023.ranlp-1.32) (Devinney et al., RANLP 2023)
ACL
- Hannah Devinney, Anton Eklund, Igor Ryazanov, and Jingwen Cai. 2023. Developing a Multilingual Corpus of Wikipedia Biographies. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 285–294, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.