@inproceedings{salmenkivi-2006-finding,
title = "Finding representative sets of dialect words for geographical regions",
author = "Salmenkivi, Marko",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/725_pdf.pdf",
abstract = "We investigate a corpus of geographical distributions of 17,126 Finnish dialect words. Our goal is to automatically find sets of words characteristic to geographical regions. Though our approach is related to the problem of dividing the investigation area into linguistically (and geographically) relatively coherent dialect regions, we do not aim at constructing more or less questionable dialect regions. Instead, we let the boundaries of the regions overlap to get insight to the degree of lexical change between adjacent areas. More concretely, we study the applicability of data clustering approaches to find sets of words with tight spatial distributions, and to cluster the extracted distributions according to their distribution areas. The extracted words belonging to the same cluster can then be utilized as a means to characterize the lexicon of the region. We also automatically pick up words with occurrences appearing in two or more areas that are geographically far from each other. These words may give valuable insight to, e.g., the study of cultural history and history of settlement.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salmenkivi-2006-finding">
<titleInfo>
<title>Finding representative sets of dialect words for geographical regions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Salmenkivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We investigate a corpus of geographical distributions of 17,126 Finnish dialect words. Our goal is to automatically find sets of words characteristic to geographical regions. Though our approach is related to the problem of dividing the investigation area into linguistically (and geographically) relatively coherent dialect regions, we do not aim at constructing more or less questionable dialect regions. Instead, we let the boundaries of the regions overlap to get insight to the degree of lexical change between adjacent areas. More concretely, we study the applicability of data clustering approaches to find sets of words with tight spatial distributions, and to cluster the extracted distributions according to their distribution areas. The extracted words belonging to the same cluster can then be utilized as a means to characterize the lexicon of the region. We also automatically pick up words with occurrences appearing in two or more areas that are geographically far from each other. These words may give valuable insight to, e.g., the study of cultural history and history of settlement.</abstract>
<identifier type="citekey">salmenkivi-2006-finding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/725_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding representative sets of dialect words for geographical regions
%A Salmenkivi, Marko
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F salmenkivi-2006-finding
%X We investigate a corpus of geographical distributions of 17,126 Finnish dialect words. Our goal is to automatically find sets of words characteristic to geographical regions. Though our approach is related to the problem of dividing the investigation area into linguistically (and geographically) relatively coherent dialect regions, we do not aim at constructing more or less questionable dialect regions. Instead, we let the boundaries of the regions overlap to get insight to the degree of lexical change between adjacent areas. More concretely, we study the applicability of data clustering approaches to find sets of words with tight spatial distributions, and to cluster the extracted distributions according to their distribution areas. The extracted words belonging to the same cluster can then be utilized as a means to characterize the lexicon of the region. We also automatically pick up words with occurrences appearing in two or more areas that are geographically far from each other. These words may give valuable insight to, e.g., the study of cultural history and history of settlement.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/725_pdf.pdf
Markdown (Informal)
[Finding representative sets of dialect words for geographical regions](http://www.lrec-conf.org/proceedings/lrec2006/pdf/725_pdf.pdf) (Salmenkivi, LREC 2006)
ACL