@inproceedings{burghardt-etal-2016-creating,
title = "Creating a Lexicon of {B}avarian Dialect by Means of {F}acebook Language Data and Crowdsourcing",
author = "Burghardt, Manuel and
Granvogl, Daniel and
Wolff, Christian",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1321",
pages = "2029--2033",
abstract = "Data acquisition in dialectology is typically a tedious task, as dialect samples of spoken language have to be collected via questionnaires or interviews. In this article, we suggest to use the {``}web as a corpus{''} approach for dialectology. We present a case study that demonstrates how authentic language data for the Bavarian dialect (ISO 639-3:bar) can be collected automatically from the social network Facebook. We also show that Facebook can be used effectively as a crowdsourcing platform, where users are willing to translate dialect words collaboratively in order to create a common lexicon of their Bavarian dialect. Key insights from the case study are summarized as {``}lessons learned{''}, together with suggestions for future enhancements of the lexicon creation approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burghardt-etal-2016-creating">
<titleInfo>
<title>Creating a Lexicon of Bavarian Dialect by Means of Facebook Language Data and Crowdsourcing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Burghardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Granvogl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Wolff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data acquisition in dialectology is typically a tedious task, as dialect samples of spoken language have to be collected via questionnaires or interviews. In this article, we suggest to use the “web as a corpus” approach for dialectology. We present a case study that demonstrates how authentic language data for the Bavarian dialect (ISO 639-3:bar) can be collected automatically from the social network Facebook. We also show that Facebook can be used effectively as a crowdsourcing platform, where users are willing to translate dialect words collaboratively in order to create a common lexicon of their Bavarian dialect. Key insights from the case study are summarized as “lessons learned”, together with suggestions for future enhancements of the lexicon creation approach.</abstract>
<identifier type="citekey">burghardt-etal-2016-creating</identifier>
<location>
<url>https://aclanthology.org/L16-1321</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2029</start>
<end>2033</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Lexicon of Bavarian Dialect by Means of Facebook Language Data and Crowdsourcing
%A Burghardt, Manuel
%A Granvogl, Daniel
%A Wolff, Christian
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F burghardt-etal-2016-creating
%X Data acquisition in dialectology is typically a tedious task, as dialect samples of spoken language have to be collected via questionnaires or interviews. In this article, we suggest to use the “web as a corpus” approach for dialectology. We present a case study that demonstrates how authentic language data for the Bavarian dialect (ISO 639-3:bar) can be collected automatically from the social network Facebook. We also show that Facebook can be used effectively as a crowdsourcing platform, where users are willing to translate dialect words collaboratively in order to create a common lexicon of their Bavarian dialect. Key insights from the case study are summarized as “lessons learned”, together with suggestions for future enhancements of the lexicon creation approach.
%U https://aclanthology.org/L16-1321
%P 2029-2033
Markdown (Informal)
[Creating a Lexicon of Bavarian Dialect by Means of Facebook Language Data and Crowdsourcing](https://aclanthology.org/L16-1321) (Burghardt et al., LREC 2016)
ACL