@inproceedings{day-etal-2008-corpus,
title = "A Corpus for Cross-Document Co-reference",
author = "Day, David and
Hitzeman, Janet and
Wick, Michael and
Crouch, Keith and
Poesio, Massimo",
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/762_paper.pdf",
abstract = "This paper describes a newly created text corpus of news articles that has been annotated for cross-document co-reference. Being able to robustly resolve references to entities across document boundaries will provide a useful capability for a variety of tasks, ranging from practical information retrieval applications to challenging research in information extraction and natural language understanding. This annotated corpus is intended to encourage the development of systems that can more accurately address this problem. A manual annotation tool was developed that allowed the complete corpus to be searched for likely co-referring entity mentions. This corpus of 257K words links mentions of co-referent people, locations and organizations (subject to some additional constraints). Each of the documents had already been annotated for within-document co-reference by the LDC as part of the ACE series of evaluations. The annotation process was bootstrapped with a string-matching-based linking procedure, and we report on some of initial experimentation with the data. The cross-document linking information will be made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="day-etal-2008-corpus">
<titleInfo>
<title>A Corpus for Cross-Document Co-reference</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Day</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janet</namePart>
<namePart type="family">Hitzeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Wick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Crouch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</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 a newly created text corpus of news articles that has been annotated for cross-document co-reference. Being able to robustly resolve references to entities across document boundaries will provide a useful capability for a variety of tasks, ranging from practical information retrieval applications to challenging research in information extraction and natural language understanding. This annotated corpus is intended to encourage the development of systems that can more accurately address this problem. A manual annotation tool was developed that allowed the complete corpus to be searched for likely co-referring entity mentions. This corpus of 257K words links mentions of co-referent people, locations and organizations (subject to some additional constraints). Each of the documents had already been annotated for within-document co-reference by the LDC as part of the ACE series of evaluations. The annotation process was bootstrapped with a string-matching-based linking procedure, and we report on some of initial experimentation with the data. The cross-document linking information will be made publicly available.</abstract>
<identifier type="citekey">day-etal-2008-corpus</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/762_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Corpus for Cross-Document Co-reference
%A Day, David
%A Hitzeman, Janet
%A Wick, Michael
%A Crouch, Keith
%A Poesio, Massimo
%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 day-etal-2008-corpus
%X This paper describes a newly created text corpus of news articles that has been annotated for cross-document co-reference. Being able to robustly resolve references to entities across document boundaries will provide a useful capability for a variety of tasks, ranging from practical information retrieval applications to challenging research in information extraction and natural language understanding. This annotated corpus is intended to encourage the development of systems that can more accurately address this problem. A manual annotation tool was developed that allowed the complete corpus to be searched for likely co-referring entity mentions. This corpus of 257K words links mentions of co-referent people, locations and organizations (subject to some additional constraints). Each of the documents had already been annotated for within-document co-reference by the LDC as part of the ACE series of evaluations. The annotation process was bootstrapped with a string-matching-based linking procedure, and we report on some of initial experimentation with the data. The cross-document linking information will be made publicly available.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/762_paper.pdf
Markdown (Informal)
[A Corpus for Cross-Document Co-reference](http://www.lrec-conf.org/proceedings/lrec2008/pdf/762_paper.pdf) (Day et al., LREC 2008)
ACL
- David Day, Janet Hitzeman, Michael Wick, Keith Crouch, and Massimo Poesio. 2008. A Corpus for Cross-Document Co-reference. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).