@inproceedings{goldhahn-quasthoff-2014-vocabulary,
title = "Vocabulary-Based Language Similarity using Web Corpora",
author = "Goldhahn, Dirk and
Quasthoff, Uwe",
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/435_Paper.pdf",
pages = "3294--3299",
abstract = "This paper will focus on the evaluation of automatic methods for quantifying language similarity. This is achieved by ascribing language similarity to the similarity of text corpora. This corpus similarity will first be determined by the resemblance of the vocabulary of languages. Thereto words or parts of them such as letter n-grams are examined. Extensions like transliteration of the text data will ensure the independence of the methods from text characteristics such as the writing system used. Further analyzes will show to what extent knowledge about the distribution of words in parallel text can be used in the context of language similarity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldhahn-quasthoff-2014-vocabulary">
<titleInfo>
<title>Vocabulary-Based Language Similarity using Web Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Goldhahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Quasthoff</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>This paper will focus on the evaluation of automatic methods for quantifying language similarity. This is achieved by ascribing language similarity to the similarity of text corpora. This corpus similarity will first be determined by the resemblance of the vocabulary of languages. Thereto words or parts of them such as letter n-grams are examined. Extensions like transliteration of the text data will ensure the independence of the methods from text characteristics such as the writing system used. Further analyzes will show to what extent knowledge about the distribution of words in parallel text can be used in the context of language similarity.</abstract>
<identifier type="citekey">goldhahn-quasthoff-2014-vocabulary</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/435_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3294</start>
<end>3299</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vocabulary-Based Language Similarity using Web Corpora
%A Goldhahn, Dirk
%A Quasthoff, Uwe
%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 goldhahn-quasthoff-2014-vocabulary
%X This paper will focus on the evaluation of automatic methods for quantifying language similarity. This is achieved by ascribing language similarity to the similarity of text corpora. This corpus similarity will first be determined by the resemblance of the vocabulary of languages. Thereto words or parts of them such as letter n-grams are examined. Extensions like transliteration of the text data will ensure the independence of the methods from text characteristics such as the writing system used. Further analyzes will show to what extent knowledge about the distribution of words in parallel text can be used in the context of language similarity.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/435_Paper.pdf
%P 3294-3299
Markdown (Informal)
[Vocabulary-Based Language Similarity using Web Corpora](http://www.lrec-conf.org/proceedings/lrec2014/pdf/435_Paper.pdf) (Goldhahn & Quasthoff, LREC 2014)
ACL
- Dirk Goldhahn and Uwe Quasthoff. 2014. Vocabulary-Based Language Similarity using Web Corpora. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3294–3299, Reykjavik, Iceland. European Language Resources Association (ELRA).