@inproceedings{grothe-etal-2008-comparative,
title = "A Comparative Study on Language Identification Methods",
author = {Grothe, Lena and
De Luca, Ernesto William and
N{\"u}rnberger, Andreas},
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/249_paper.pdf",
abstract = "In this paper we present two experiments conducted for comparison of different language identification algorithms. Short words-, frequent words- and n-gram-based approaches are considered and combined with the Ad-Hoc Ranking classification method. The language identification process can be subdivided into two main steps: first a document model is generated for the document and a language model for the language; second the language of the document is determined on the basis of the language model and is added to the document as additional information. In this work we present our evaluation results and discuss the importance of a dynamic value for the out-of-place measure.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grothe-etal-2008-comparative">
<titleInfo>
<title>A Comparative Study on Language Identification Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Grothe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">William</namePart>
<namePart type="family">De Luca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Nürnberger</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>In this paper we present two experiments conducted for comparison of different language identification algorithms. Short words-, frequent words- and n-gram-based approaches are considered and combined with the Ad-Hoc Ranking classification method. The language identification process can be subdivided into two main steps: first a document model is generated for the document and a language model for the language; second the language of the document is determined on the basis of the language model and is added to the document as additional information. In this work we present our evaluation results and discuss the importance of a dynamic value for the out-of-place measure.</abstract>
<identifier type="citekey">grothe-etal-2008-comparative</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/249_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparative Study on Language Identification Methods
%A Grothe, Lena
%A De Luca, Ernesto William
%A Nürnberger, Andreas
%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 grothe-etal-2008-comparative
%X In this paper we present two experiments conducted for comparison of different language identification algorithms. Short words-, frequent words- and n-gram-based approaches are considered and combined with the Ad-Hoc Ranking classification method. The language identification process can be subdivided into two main steps: first a document model is generated for the document and a language model for the language; second the language of the document is determined on the basis of the language model and is added to the document as additional information. In this work we present our evaluation results and discuss the importance of a dynamic value for the out-of-place measure.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/249_paper.pdf
Markdown (Informal)
[A Comparative Study on Language Identification Methods](http://www.lrec-conf.org/proceedings/lrec2008/pdf/249_paper.pdf) (Grothe et al., LREC 2008)
ACL
- Lena Grothe, Ernesto William De Luca, and Andreas Nürnberger. 2008. A Comparative Study on Language Identification Methods. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).