@inproceedings{guillou-etal-2014-parcor,
title = "{P}ar{C}or 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical {MT}",
author = {Guillou, Liane and
Hardmeier, Christian and
Smith, Aaron and
Tiedemann, J{\"o}rg and
Webber, Bonnie},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/298_Paper.pdf",
pages = "3191--3198",
abstract = "We present ParCor, a parallel corpus of texts in which pronoun coreference ― reduced coreference in which pronouns are used as referring expressions ― has been annotated. The corpus is intended to be used both as a resource from which to learn systematic differences in pronoun use between languages and ultimately for developing and testing informed Statistical Machine Translation systems aimed at addressing the problem of pronoun coreference in translation. At present, the corpus consists of a collection of parallel English-German documents from two different text genres: TED Talks (transcribed planned speech), and EU Bookshop publications (written text). All documents in the corpus have been manually annotated with respect to the type and location of each pronoun and, where relevant, its antecedent. We provide details of the texts that we selected, the guidelines and tools used to support annotation and some corpus statistics. The texts in the corpus have already been translated into many languages, and we plan to expand the corpus into these other languages, as well as other genres, in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guillou-etal-2014-parcor">
<titleInfo>
<title>ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liane</namePart>
<namePart type="family">Guillou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present ParCor, a parallel corpus of texts in which pronoun coreference ― reduced coreference in which pronouns are used as referring expressions ― has been annotated. The corpus is intended to be used both as a resource from which to learn systematic differences in pronoun use between languages and ultimately for developing and testing informed Statistical Machine Translation systems aimed at addressing the problem of pronoun coreference in translation. At present, the corpus consists of a collection of parallel English-German documents from two different text genres: TED Talks (transcribed planned speech), and EU Bookshop publications (written text). All documents in the corpus have been manually annotated with respect to the type and location of each pronoun and, where relevant, its antecedent. We provide details of the texts that we selected, the guidelines and tools used to support annotation and some corpus statistics. The texts in the corpus have already been translated into many languages, and we plan to expand the corpus into these other languages, as well as other genres, in the future.</abstract>
<identifier type="citekey">guillou-etal-2014-parcor</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/298_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3191</start>
<end>3198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT
%A Guillou, Liane
%A Hardmeier, Christian
%A Smith, Aaron
%A Tiedemann, Jörg
%A Webber, Bonnie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F guillou-etal-2014-parcor
%X We present ParCor, a parallel corpus of texts in which pronoun coreference ― reduced coreference in which pronouns are used as referring expressions ― has been annotated. The corpus is intended to be used both as a resource from which to learn systematic differences in pronoun use between languages and ultimately for developing and testing informed Statistical Machine Translation systems aimed at addressing the problem of pronoun coreference in translation. At present, the corpus consists of a collection of parallel English-German documents from two different text genres: TED Talks (transcribed planned speech), and EU Bookshop publications (written text). All documents in the corpus have been manually annotated with respect to the type and location of each pronoun and, where relevant, its antecedent. We provide details of the texts that we selected, the guidelines and tools used to support annotation and some corpus statistics. The texts in the corpus have already been translated into many languages, and we plan to expand the corpus into these other languages, as well as other genres, in the future.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/298_Paper.pdf
%P 3191-3198
Markdown (Informal)
[ParCor 1.0: A Parallel Pronoun-Coreference Corpus to Support Statistical MT](http://www.lrec-conf.org/proceedings/lrec2014/pdf/298_Paper.pdf) (Guillou et al., LREC 2014)
ACL