@inproceedings{nazar-etal-2008-suite,
title = "A Suite to Compile and Analyze an {LSP} Corpus",
author = "Nazar, Rogelio and
Vivaldi, Jorge and
Cabr{\'e}, Teresa",
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/296_paper.pdf",
abstract = "This paper presents a series of tools for the extraction of specialized corpora from the web and its subsequent analysis mainly with statistical techniques. It is an integrated system of original as well as standard tools and has a modular conception that facilitates its re-integration on different systems. The first part of the paper describes the original techniques, which are devoted to the categorization of documents as relevant or irrelevant to the corpus under construction, considering relevant a specialized document of the selected technical domain. Evaluation figures are provided for the original part, but not for the second part involving the analysis of the corpus, which is composed of algorithms that are well known in the field of Natural Language Processing, such as Kwic search, measures of vocabulary richness, the sorting of n-grams by frequency of occurrence or by measures of statistical association, distribution or similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nazar-etal-2008-suite">
<titleInfo>
<title>A Suite to Compile and Analyze an LSP Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rogelio</namePart>
<namePart type="family">Nazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Vivaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Cabré</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 presents a series of tools for the extraction of specialized corpora from the web and its subsequent analysis mainly with statistical techniques. It is an integrated system of original as well as standard tools and has a modular conception that facilitates its re-integration on different systems. The first part of the paper describes the original techniques, which are devoted to the categorization of documents as relevant or irrelevant to the corpus under construction, considering relevant a specialized document of the selected technical domain. Evaluation figures are provided for the original part, but not for the second part involving the analysis of the corpus, which is composed of algorithms that are well known in the field of Natural Language Processing, such as Kwic search, measures of vocabulary richness, the sorting of n-grams by frequency of occurrence or by measures of statistical association, distribution or similarity.</abstract>
<identifier type="citekey">nazar-etal-2008-suite</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/296_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Suite to Compile and Analyze an LSP Corpus
%A Nazar, Rogelio
%A Vivaldi, Jorge
%A Cabré, Teresa
%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 nazar-etal-2008-suite
%X This paper presents a series of tools for the extraction of specialized corpora from the web and its subsequent analysis mainly with statistical techniques. It is an integrated system of original as well as standard tools and has a modular conception that facilitates its re-integration on different systems. The first part of the paper describes the original techniques, which are devoted to the categorization of documents as relevant or irrelevant to the corpus under construction, considering relevant a specialized document of the selected technical domain. Evaluation figures are provided for the original part, but not for the second part involving the analysis of the corpus, which is composed of algorithms that are well known in the field of Natural Language Processing, such as Kwic search, measures of vocabulary richness, the sorting of n-grams by frequency of occurrence or by measures of statistical association, distribution or similarity.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/296_paper.pdf
Markdown (Informal)
[A Suite to Compile and Analyze an LSP Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/296_paper.pdf) (Nazar et al., LREC 2008)
ACL
- Rogelio Nazar, Jorge Vivaldi, and Teresa Cabré. 2008. A Suite to Compile and Analyze an LSP Corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).