@inproceedings{klang-nugues-2016-pairing,
title = "Pairing {W}ikipedia Articles Across Languages",
author = "Klang, Marcus and
Nugues, Pierre",
editor = "Choi, Key-Sun and
Unger, Christina and
Vossen, Piek and
Kim, Jin-Dong and
Kando, Noriko and
Ngonga Ngomo, Axel-Cyrille",
booktitle = "Proceedings of the Open Knowledge Base and Question Answering Workshop ({OKBQA} 2016)",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4410",
pages = "72--76",
abstract = "Wikipedia has become a reference knowledge source for scores of NLP applications. One of its invaluable features lies in its multilingual nature, where articles on a same entity or concept can have from one to more than 200 different versions. The interlinking of language versions in Wikipedia has undergone a major renewal with the advent of Wikidata, a unified scheme to identify entities and their properties using unique numbers. However, as the interlinking is still manually carried out by thousands of editors across the globe, errors may creep in the assignment of entities. In this paper, we describe an optimization technique to match automatically language versions of articles, and hence entities, that is only based on bags of words and anchors. We created a dataset of all the articles on persons we extracted from Wikipedia in six languages: English, French, German, Russian, Spanish, and Swedish. We report a correct match of at least 94.3{\%} on each pair.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klang-nugues-2016-pairing">
<titleInfo>
<title>Pairing Wikipedia Articles Across Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Klang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Nugues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Unger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Dong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noriko</namePart>
<namePart type="family">Kando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel-Cyrille</namePart>
<namePart type="family">Ngonga Ngomo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Wikipedia has become a reference knowledge source for scores of NLP applications. One of its invaluable features lies in its multilingual nature, where articles on a same entity or concept can have from one to more than 200 different versions. The interlinking of language versions in Wikipedia has undergone a major renewal with the advent of Wikidata, a unified scheme to identify entities and their properties using unique numbers. However, as the interlinking is still manually carried out by thousands of editors across the globe, errors may creep in the assignment of entities. In this paper, we describe an optimization technique to match automatically language versions of articles, and hence entities, that is only based on bags of words and anchors. We created a dataset of all the articles on persons we extracted from Wikipedia in six languages: English, French, German, Russian, Spanish, and Swedish. We report a correct match of at least 94.3% on each pair.</abstract>
<identifier type="citekey">klang-nugues-2016-pairing</identifier>
<location>
<url>https://aclanthology.org/W16-4410</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>72</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pairing Wikipedia Articles Across Languages
%A Klang, Marcus
%A Nugues, Pierre
%Y Choi, Key-Sun
%Y Unger, Christina
%Y Vossen, Piek
%Y Kim, Jin-Dong
%Y Kando, Noriko
%Y Ngonga Ngomo, Axel-Cyrille
%S Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F klang-nugues-2016-pairing
%X Wikipedia has become a reference knowledge source for scores of NLP applications. One of its invaluable features lies in its multilingual nature, where articles on a same entity or concept can have from one to more than 200 different versions. The interlinking of language versions in Wikipedia has undergone a major renewal with the advent of Wikidata, a unified scheme to identify entities and their properties using unique numbers. However, as the interlinking is still manually carried out by thousands of editors across the globe, errors may creep in the assignment of entities. In this paper, we describe an optimization technique to match automatically language versions of articles, and hence entities, that is only based on bags of words and anchors. We created a dataset of all the articles on persons we extracted from Wikipedia in six languages: English, French, German, Russian, Spanish, and Swedish. We report a correct match of at least 94.3% on each pair.
%U https://aclanthology.org/W16-4410
%P 72-76
Markdown (Informal)
[Pairing Wikipedia Articles Across Languages](https://aclanthology.org/W16-4410) (Klang & Nugues, 2016)
ACL
- Marcus Klang and Pierre Nugues. 2016. Pairing Wikipedia Articles Across Languages. In Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016), pages 72–76, Osaka, Japan. The COLING 2016 Organizing Committee.