@inproceedings{rocha-souza-etal-2020-identification,
title = "Identification of Indigenous Knowledge Concepts through Semantic Networks, Spelling Tools and Word Embeddings",
author = "Rocha Souza, Renato and
Dorn, Amelie and
Piringer, Barbara and
Wandl-Vogt, Eveline",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.118",
pages = "943--947",
abstract = {In order to access indigenous, regional knowledge contained in language corpora, semantic tools and network methods are most typically employed. In this paper we present an approach for the identification of dialectal variations of words, or words that do not pertain to High German, on the example of non-standard language legacy collection questionnaires of the Bavarian Dialects in Austria (DB{\"O}). Based on selected cultural categories relevant to the wider project context, common words from each of these cultural categories and their lemmas using GermaLemma were identified. Through word embedding models the semantic vicinity of each word was explored, followed by the use of German Wordnet (Germanet) and the Hunspell tool. Whilst none of these tools have a comprehensive coverage of standard German words, they serve as an indication of dialects in specific semantic hierarchies. Methods and tools applied in this study may serve as an example for other similar projects dealing with non-standard or endangered language collections, aiming to access, analyze and ultimately preserve native regional language heritage.},
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rocha-souza-etal-2020-identification">
<titleInfo>
<title>Identification of Indigenous Knowledge Concepts through Semantic Networks, Spelling Tools and Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renato</namePart>
<namePart type="family">Rocha Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amelie</namePart>
<namePart type="family">Dorn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Piringer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eveline</namePart>
<namePart type="family">Wandl-Vogt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In order to access indigenous, regional knowledge contained in language corpora, semantic tools and network methods are most typically employed. In this paper we present an approach for the identification of dialectal variations of words, or words that do not pertain to High German, on the example of non-standard language legacy collection questionnaires of the Bavarian Dialects in Austria (DBÖ). Based on selected cultural categories relevant to the wider project context, common words from each of these cultural categories and their lemmas using GermaLemma were identified. Through word embedding models the semantic vicinity of each word was explored, followed by the use of German Wordnet (Germanet) and the Hunspell tool. Whilst none of these tools have a comprehensive coverage of standard German words, they serve as an indication of dialects in specific semantic hierarchies. Methods and tools applied in this study may serve as an example for other similar projects dealing with non-standard or endangered language collections, aiming to access, analyze and ultimately preserve native regional language heritage.</abstract>
<identifier type="citekey">rocha-souza-etal-2020-identification</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.118</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>943</start>
<end>947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identification of Indigenous Knowledge Concepts through Semantic Networks, Spelling Tools and Word Embeddings
%A Rocha Souza, Renato
%A Dorn, Amelie
%A Piringer, Barbara
%A Wandl-Vogt, Eveline
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F rocha-souza-etal-2020-identification
%X In order to access indigenous, regional knowledge contained in language corpora, semantic tools and network methods are most typically employed. In this paper we present an approach for the identification of dialectal variations of words, or words that do not pertain to High German, on the example of non-standard language legacy collection questionnaires of the Bavarian Dialects in Austria (DBÖ). Based on selected cultural categories relevant to the wider project context, common words from each of these cultural categories and their lemmas using GermaLemma were identified. Through word embedding models the semantic vicinity of each word was explored, followed by the use of German Wordnet (Germanet) and the Hunspell tool. Whilst none of these tools have a comprehensive coverage of standard German words, they serve as an indication of dialects in specific semantic hierarchies. Methods and tools applied in this study may serve as an example for other similar projects dealing with non-standard or endangered language collections, aiming to access, analyze and ultimately preserve native regional language heritage.
%U https://aclanthology.org/2020.lrec-1.118
%P 943-947
Markdown (Informal)
[Identification of Indigenous Knowledge Concepts through Semantic Networks, Spelling Tools and Word Embeddings](https://aclanthology.org/2020.lrec-1.118) (Rocha Souza et al., LREC 2020)
ACL