@inproceedings{ljubesic-toral-2014-cawac,
title = "ca{W}a{C} {--} A web corpus of {C}atalan and its application to language modeling and machine translation",
author = "Ljube{\v{s}}i{\'c}, Nikola and
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/841_Paper.pdf",
pages = "1728--1732",
abstract = "In this paper we present the construction process of a web corpus of Catalan built from the content of the .cat top-level domain. For collecting and processing data we use the Brno pipeline with the spiderling crawler and its accompanying tools. To the best of our knowledge the corpus represents the largest existing corpus of Catalan containing 687 million words, which is a significant increase given that until now the biggest corpus of Catalan, CuCWeb, counts 166 million words. We evaluate the resulting resource on the tasks of language modeling and statistical machine translation (SMT) by calculating LM perplexity and incorporating the LM in the SMT pipeline. We compare language models trained on different subsets of the resource with those trained on the Catalan Wikipedia and the target side of the parallel data used to train the SMT system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-toral-2014-cawac">
<titleInfo>
<title>caWaC – A web corpus of Catalan and its application to language modeling and machine translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>In this paper we present the construction process of a web corpus of Catalan built from the content of the .cat top-level domain. For collecting and processing data we use the Brno pipeline with the spiderling crawler and its accompanying tools. To the best of our knowledge the corpus represents the largest existing corpus of Catalan containing 687 million words, which is a significant increase given that until now the biggest corpus of Catalan, CuCWeb, counts 166 million words. We evaluate the resulting resource on the tasks of language modeling and statistical machine translation (SMT) by calculating LM perplexity and incorporating the LM in the SMT pipeline. We compare language models trained on different subsets of the resource with those trained on the Catalan Wikipedia and the target side of the parallel data used to train the SMT system.</abstract>
<identifier type="citekey">ljubesic-toral-2014-cawac</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/841_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1728</start>
<end>1732</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T caWaC – A web corpus of Catalan and its application to language modeling and machine translation
%A Ljubešić, Nikola
%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 ljubesic-toral-2014-cawac
%X In this paper we present the construction process of a web corpus of Catalan built from the content of the .cat top-level domain. For collecting and processing data we use the Brno pipeline with the spiderling crawler and its accompanying tools. To the best of our knowledge the corpus represents the largest existing corpus of Catalan containing 687 million words, which is a significant increase given that until now the biggest corpus of Catalan, CuCWeb, counts 166 million words. We evaluate the resulting resource on the tasks of language modeling and statistical machine translation (SMT) by calculating LM perplexity and incorporating the LM in the SMT pipeline. We compare language models trained on different subsets of the resource with those trained on the Catalan Wikipedia and the target side of the parallel data used to train the SMT system.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/841_Paper.pdf
%P 1728-1732
Markdown (Informal)
[caWaC – A web corpus of Catalan and its application to language modeling and machine translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/841_Paper.pdf) (Ljubešić & Toral, LREC 2014)
ACL