@inproceedings{spitkovsky-chang-2012-cross,
title = "A Cross-Lingual Dictionary for {E}nglish {W}ikipedia Concepts",
author = "Spitkovsky, Valentin I. and
Chang, Angel X.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/266_Paper.pdf",
pages = "3168--3175",
abstract = "We present a resource for automatically associating strings of text with English Wikipedia concepts. Our machinery is bi-directional, in the sense that it uses the same fundamental probabilistic methods to map strings to empirical distributions over Wikipedia articles as it does to map article URLs to distributions over short, language-independent strings of natural language text. For maximal inter-operability, we release our resource as a set of flat line-based text files, lexicographically sorted and encoded with UTF-8. These files capture joint probability distributions underlying concepts (we use the terms article, concept and Wikipedia URL interchangeably) and associated snippets of text, as well as other features that can come in handy when working with Wikipedia articles and related information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spitkovsky-chang-2012-cross">
<titleInfo>
<title>A Cross-Lingual Dictionary for English Wikipedia Concepts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Spitkovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="given">X</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a resource for automatically associating strings of text with English Wikipedia concepts. Our machinery is bi-directional, in the sense that it uses the same fundamental probabilistic methods to map strings to empirical distributions over Wikipedia articles as it does to map article URLs to distributions over short, language-independent strings of natural language text. For maximal inter-operability, we release our resource as a set of flat line-based text files, lexicographically sorted and encoded with UTF-8. These files capture joint probability distributions underlying concepts (we use the terms article, concept and Wikipedia URL interchangeably) and associated snippets of text, as well as other features that can come in handy when working with Wikipedia articles and related information.</abstract>
<identifier type="citekey">spitkovsky-chang-2012-cross</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/266_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3168</start>
<end>3175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Cross-Lingual Dictionary for English Wikipedia Concepts
%A Spitkovsky, Valentin I.
%A Chang, Angel X.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F spitkovsky-chang-2012-cross
%X We present a resource for automatically associating strings of text with English Wikipedia concepts. Our machinery is bi-directional, in the sense that it uses the same fundamental probabilistic methods to map strings to empirical distributions over Wikipedia articles as it does to map article URLs to distributions over short, language-independent strings of natural language text. For maximal inter-operability, we release our resource as a set of flat line-based text files, lexicographically sorted and encoded with UTF-8. These files capture joint probability distributions underlying concepts (we use the terms article, concept and Wikipedia URL interchangeably) and associated snippets of text, as well as other features that can come in handy when working with Wikipedia articles and related information.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/266_Paper.pdf
%P 3168-3175
Markdown (Informal)
[A Cross-Lingual Dictionary for English Wikipedia Concepts](http://www.lrec-conf.org/proceedings/lrec2012/pdf/266_Paper.pdf) (Spitkovsky & Chang, LREC 2012)
ACL
- Valentin I. Spitkovsky and Angel X. Chang. 2012. A Cross-Lingual Dictionary for English Wikipedia Concepts. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3168–3175, Istanbul, Turkey. European Language Resources Association (ELRA).