@inproceedings{toral-2014-tlaxcala,
title = "{TLAXCALA}: a multilingual corpus of independent news",
author = "Toral, Antonio",
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/1134_Paper.pdf",
pages = "3689--3692",
abstract = "We acquire corpora from the domain of independent news from the Tlaxcala website. We build monolingual corpora for 15 languages and parallel corpora for all the combinations of those 15 languages. These corpora include languages for which only very limited such resources exist (e.g. Tamazight). We present the acquisition process in detail and we also present detailed statistics of the produced corpora, concerning mainly quantitative dimensions such as the size of the corpora per language (for the monolingual corpora) and per language pair (for the parallel corpora). To the best of our knowledge, these are the first publicly available parallel and monolingual corpora for the domain of independent news. We also create models for unsupervised sentence splitting for all the languages of the study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toral-2014-tlaxcala">
<titleInfo>
<title>TLAXCALA: a multilingual corpus of independent news</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</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 acquire corpora from the domain of independent news from the Tlaxcala website. We build monolingual corpora for 15 languages and parallel corpora for all the combinations of those 15 languages. These corpora include languages for which only very limited such resources exist (e.g. Tamazight). We present the acquisition process in detail and we also present detailed statistics of the produced corpora, concerning mainly quantitative dimensions such as the size of the corpora per language (for the monolingual corpora) and per language pair (for the parallel corpora). To the best of our knowledge, these are the first publicly available parallel and monolingual corpora for the domain of independent news. We also create models for unsupervised sentence splitting for all the languages of the study.</abstract>
<identifier type="citekey">toral-2014-tlaxcala</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1134_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3689</start>
<end>3692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TLAXCALA: a multilingual corpus of independent news
%A Toral, Antonio
%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 toral-2014-tlaxcala
%X We acquire corpora from the domain of independent news from the Tlaxcala website. We build monolingual corpora for 15 languages and parallel corpora for all the combinations of those 15 languages. These corpora include languages for which only very limited such resources exist (e.g. Tamazight). We present the acquisition process in detail and we also present detailed statistics of the produced corpora, concerning mainly quantitative dimensions such as the size of the corpora per language (for the monolingual corpora) and per language pair (for the parallel corpora). To the best of our knowledge, these are the first publicly available parallel and monolingual corpora for the domain of independent news. We also create models for unsupervised sentence splitting for all the languages of the study.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1134_Paper.pdf
%P 3689-3692
Markdown (Informal)
[TLAXCALA: a multilingual corpus of independent news](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1134_Paper.pdf) (Toral, LREC 2014)
ACL
- Antonio Toral. 2014. TLAXCALA: a multilingual corpus of independent news. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3689–3692, Reykjavik, Iceland. European Language Resources Association (ELRA).