@inproceedings{seddah-etal-2012-ubiquitous,
title = "Ubiquitous Usage of a Broad Coverage {F}rench Corpus: Processing the {E}st {R}epublicain corpus",
author = "Seddah, Djam{\'e} and
Candito, Marie and
Crabb{\'e}, Benoit and
Anguiano, Enrique Henestroza",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf",
pages = "3249--3254",
abstract = "In this paper, we introduce a set of resources that we have derived from the EST R{\'E}PUBLICAIN CORPUS, a large, freely-available collection of regional newspaper articles in French, totaling 150 million words. Our resources are the result of a full NLP treatment of the EST R{\'E}PUBLICAIN CORPUS: handling of multi-word expressions, lemmatization, part-of-speech tagging, and syntactic parsing. Processing of the corpus is carried out using statistical machine-learning approaches - joint model of data driven lemmatization and part- of-speech tagging, PCFG-LA and dependency based models for parsing - that have been shown to achieve state-of-the-art performance when evaluated on the French Treebank. Our derived resources are made freely available, and released according to the original Creative Common license for the EST R{\'E}PUBLICAIN CORPUS. We additionally provide an overview of the use of these resources in various applications, in particular the use of generated word clusters from the corpus to alleviate lexical data sparseness for statistical parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seddah-etal-2012-ubiquitous">
<titleInfo>
<title>Ubiquitous Usage of a Broad Coverage French Corpus: Processing the Est Republicain corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Candito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Crabbé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="given">Henestroza</namePart>
<namePart type="family">Anguiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce a set of resources that we have derived from the EST RÉPUBLICAIN CORPUS, a large, freely-available collection of regional newspaper articles in French, totaling 150 million words. Our resources are the result of a full NLP treatment of the EST RÉPUBLICAIN CORPUS: handling of multi-word expressions, lemmatization, part-of-speech tagging, and syntactic parsing. Processing of the corpus is carried out using statistical machine-learning approaches - joint model of data driven lemmatization and part- of-speech tagging, PCFG-LA and dependency based models for parsing - that have been shown to achieve state-of-the-art performance when evaluated on the French Treebank. Our derived resources are made freely available, and released according to the original Creative Common license for the EST RÉPUBLICAIN CORPUS. We additionally provide an overview of the use of these resources in various applications, in particular the use of generated word clusters from the corpus to alleviate lexical data sparseness for statistical parsing.</abstract>
<identifier type="citekey">seddah-etal-2012-ubiquitous</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3249</start>
<end>3254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ubiquitous Usage of a Broad Coverage French Corpus: Processing the Est Republicain corpus
%A Seddah, Djamé
%A Candito, Marie
%A Crabbé, Benoit
%A Anguiano, Enrique Henestroza
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F seddah-etal-2012-ubiquitous
%X In this paper, we introduce a set of resources that we have derived from the EST RÉPUBLICAIN CORPUS, a large, freely-available collection of regional newspaper articles in French, totaling 150 million words. Our resources are the result of a full NLP treatment of the EST RÉPUBLICAIN CORPUS: handling of multi-word expressions, lemmatization, part-of-speech tagging, and syntactic parsing. Processing of the corpus is carried out using statistical machine-learning approaches - joint model of data driven lemmatization and part- of-speech tagging, PCFG-LA and dependency based models for parsing - that have been shown to achieve state-of-the-art performance when evaluated on the French Treebank. Our derived resources are made freely available, and released according to the original Creative Common license for the EST RÉPUBLICAIN CORPUS. We additionally provide an overview of the use of these resources in various applications, in particular the use of generated word clusters from the corpus to alleviate lexical data sparseness for statistical parsing.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf
%P 3249-3254
Markdown (Informal)
[Ubiquitous Usage of a Broad Coverage French Corpus: Processing the Est Republicain corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1130_Paper.pdf) (Seddah et al., LREC 2012)
ACL