@inproceedings{atserias-etal-2008-semantically,
title = "Semantically Annotated Snapshot of the {E}nglish {W}ikipedia",
author = "Atserias, Jordi and
Zaragoza, Hugo and
Ciaramita, Massimiliano and
Attardi, Giuseppe",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf",
abstract = "This paper describes SW1, the first version of a semantically annotated snapshot of the English Wikipedia. In recent years Wikipedia has become a valuable resource for both the Natural Language Processing (NLP) community and the Information Retrieval (IR) community. Although NLP technology for processing Wikipedia already exists, not all researchers and developers have the computational resources to process such a volume of information. Moreover, the use of different versions of Wikipedia processed differently might make it difficult to compare results. The aim of this work is to provide easy access to syntactic and semantic annotations for researchers of both NLP and IR communities by building a reference corpus to homogenize experiments and make results comparable. These resources, a semantically annotated corpus and a entity containment derived graph, are licensed under the GNU Free Documentation License and available from \url{http://www.yr-bcn.es/semanticWikipedia}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="atserias-etal-2008-semantically">
<titleInfo>
<title>Semantically Annotated Snapshot of the English Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jordi</namePart>
<namePart type="family">Atserias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Zaragoza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimiliano</namePart>
<namePart type="family">Ciaramita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes SW1, the first version of a semantically annotated snapshot of the English Wikipedia. In recent years Wikipedia has become a valuable resource for both the Natural Language Processing (NLP) community and the Information Retrieval (IR) community. Although NLP technology for processing Wikipedia already exists, not all researchers and developers have the computational resources to process such a volume of information. Moreover, the use of different versions of Wikipedia processed differently might make it difficult to compare results. The aim of this work is to provide easy access to syntactic and semantic annotations for researchers of both NLP and IR communities by building a reference corpus to homogenize experiments and make results comparable. These resources, a semantically annotated corpus and a entity containment derived graph, are licensed under the GNU Free Documentation License and available from http://www.yr-bcn.es/semanticWikipedia</abstract>
<identifier type="citekey">atserias-etal-2008-semantically</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantically Annotated Snapshot of the English Wikipedia
%A Atserias, Jordi
%A Zaragoza, Hugo
%A Ciaramita, Massimiliano
%A Attardi, Giuseppe
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F atserias-etal-2008-semantically
%X This paper describes SW1, the first version of a semantically annotated snapshot of the English Wikipedia. In recent years Wikipedia has become a valuable resource for both the Natural Language Processing (NLP) community and the Information Retrieval (IR) community. Although NLP technology for processing Wikipedia already exists, not all researchers and developers have the computational resources to process such a volume of information. Moreover, the use of different versions of Wikipedia processed differently might make it difficult to compare results. The aim of this work is to provide easy access to syntactic and semantic annotations for researchers of both NLP and IR communities by building a reference corpus to homogenize experiments and make results comparable. These resources, a semantically annotated corpus and a entity containment derived graph, are licensed under the GNU Free Documentation License and available from http://www.yr-bcn.es/semanticWikipedia
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf
Markdown (Informal)
[Semantically Annotated Snapshot of the English Wikipedia](http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf) (Atserias et al., LREC 2008)
ACL
- Jordi Atserias, Hugo Zaragoza, Massimiliano Ciaramita, and Giuseppe Attardi. 2008. Semantically Annotated Snapshot of the English Wikipedia. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).