@inproceedings{quasthoff-etal-2014-high,
title = "High Quality Word Lists as a Resource for Multiple Purposes",
author = "Quasthoff, Uwe and
Goldhahn, Dirk and
Eckart, Thomas and
Hallsteinsd{\'o}ttir, Erla and
Fiedler, Sabine",
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/657_Paper.pdf",
pages = "2816--2819",
abstract = "Since 2011 the comprehensive, electronically available sources of the Leipzig Corpora Collection have been used consistently for the compilation of high quality word lists. The underlying corpora include newspaper texts, Wikipedia articles and other randomly collected Web texts. For many of the languages featured in this collection, it is the first comprehensive compilation to use a large-scale empirical base. The word lists have been used to compile dictionaries with comparable frequency data in the Frequency Dictionaries series. This includes frequency data of up to 1,000,000 word forms presented in alphabetical order. This article provides an introductory description of the data and the methodological approach used. In addition, language-specific statistical information is provided with regard to letters, word structure and structural changes. Such high quality word lists also provide the opportunity to explore comparative linguistic topics and such monolingual issues as studies of word formation and frequency-based examinations of lexical areas for use in dictionaries or language teaching. The results presented here can provide initial suggestions for subsequent work in several areas of research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="quasthoff-etal-2014-high">
<titleInfo>
<title>High Quality Word Lists as a Resource for Multiple Purposes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uwe</namePart>
<namePart type="family">Quasthoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Thomas</namePart>
<namePart type="family">Eckart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erla</namePart>
<namePart type="family">Hallsteinsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Fiedler</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>Since 2011 the comprehensive, electronically available sources of the Leipzig Corpora Collection have been used consistently for the compilation of high quality word lists. The underlying corpora include newspaper texts, Wikipedia articles and other randomly collected Web texts. For many of the languages featured in this collection, it is the first comprehensive compilation to use a large-scale empirical base. The word lists have been used to compile dictionaries with comparable frequency data in the Frequency Dictionaries series. This includes frequency data of up to 1,000,000 word forms presented in alphabetical order. This article provides an introductory description of the data and the methodological approach used. In addition, language-specific statistical information is provided with regard to letters, word structure and structural changes. Such high quality word lists also provide the opportunity to explore comparative linguistic topics and such monolingual issues as studies of word formation and frequency-based examinations of lexical areas for use in dictionaries or language teaching. The results presented here can provide initial suggestions for subsequent work in several areas of research.</abstract>
<identifier type="citekey">quasthoff-etal-2014-high</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/657_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2816</start>
<end>2819</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T High Quality Word Lists as a Resource for Multiple Purposes
%A Quasthoff, Uwe
%A Goldhahn, Dirk
%A Eckart, Thomas
%A Hallsteinsdóttir, Erla
%A Fiedler, Sabine
%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 quasthoff-etal-2014-high
%X Since 2011 the comprehensive, electronically available sources of the Leipzig Corpora Collection have been used consistently for the compilation of high quality word lists. The underlying corpora include newspaper texts, Wikipedia articles and other randomly collected Web texts. For many of the languages featured in this collection, it is the first comprehensive compilation to use a large-scale empirical base. The word lists have been used to compile dictionaries with comparable frequency data in the Frequency Dictionaries series. This includes frequency data of up to 1,000,000 word forms presented in alphabetical order. This article provides an introductory description of the data and the methodological approach used. In addition, language-specific statistical information is provided with regard to letters, word structure and structural changes. Such high quality word lists also provide the opportunity to explore comparative linguistic topics and such monolingual issues as studies of word formation and frequency-based examinations of lexical areas for use in dictionaries or language teaching. The results presented here can provide initial suggestions for subsequent work in several areas of research.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/657_Paper.pdf
%P 2816-2819
Markdown (Informal)
[High Quality Word Lists as a Resource for Multiple Purposes](http://www.lrec-conf.org/proceedings/lrec2014/pdf/657_Paper.pdf) (Quasthoff et al., LREC 2014)
ACL
- Uwe Quasthoff, Dirk Goldhahn, Thomas Eckart, Erla Hallsteinsdóttir, and Sabine Fiedler. 2014. High Quality Word Lists as a Resource for Multiple Purposes. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2816–2819, Reykjavik, Iceland. European Language Resources Association (ELRA).