@inproceedings{jettka-lehmberg-2020-towards,
title = "Towards Flexible Cross-Resource Exploitation of Heterogeneous Language Documentation Data",
author = "Jettka, Daniel and
Lehmberg, Timm",
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-1.354",
pages = "2901--2905",
abstract = "This paper reports on challenges and solution approaches in the development of methods for language resource overarching data analysis in the field of language documentation. It is based on the successful outcomes of the initial phase of an 18 year long-term project on lesser resourced and mostly endangered indigenous languages of the Northern Eurasian area, which included the finalization and publication of multiple language corpora and additional language resources. While aiming at comprehensive cross-resource data analysis, the project at the same time is confronted with a dynamic and complex resource landscape, especially resulting from a vast amount of multi-layered information stored in the form of analogue primary data in different widespread archives on the territory of the Russian Federation. The methods described aim at solving the tension between unification of data sets and vocabularies on the one hand and maximum openness for the integration of future resources and adaption of external information on the other hand.",
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="jettka-lehmberg-2020-towards">
<titleInfo>
<title>Towards Flexible Cross-Resource Exploitation of Heterogeneous Language Documentation Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Jettka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timm</namePart>
<namePart type="family">Lehmberg</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>This paper reports on challenges and solution approaches in the development of methods for language resource overarching data analysis in the field of language documentation. It is based on the successful outcomes of the initial phase of an 18 year long-term project on lesser resourced and mostly endangered indigenous languages of the Northern Eurasian area, which included the finalization and publication of multiple language corpora and additional language resources. While aiming at comprehensive cross-resource data analysis, the project at the same time is confronted with a dynamic and complex resource landscape, especially resulting from a vast amount of multi-layered information stored in the form of analogue primary data in different widespread archives on the territory of the Russian Federation. The methods described aim at solving the tension between unification of data sets and vocabularies on the one hand and maximum openness for the integration of future resources and adaption of external information on the other hand.</abstract>
<identifier type="citekey">jettka-lehmberg-2020-towards</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.354</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2901</start>
<end>2905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Flexible Cross-Resource Exploitation of Heterogeneous Language Documentation Data
%A Jettka, Daniel
%A Lehmberg, Timm
%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 jettka-lehmberg-2020-towards
%X This paper reports on challenges and solution approaches in the development of methods for language resource overarching data analysis in the field of language documentation. It is based on the successful outcomes of the initial phase of an 18 year long-term project on lesser resourced and mostly endangered indigenous languages of the Northern Eurasian area, which included the finalization and publication of multiple language corpora and additional language resources. While aiming at comprehensive cross-resource data analysis, the project at the same time is confronted with a dynamic and complex resource landscape, especially resulting from a vast amount of multi-layered information stored in the form of analogue primary data in different widespread archives on the territory of the Russian Federation. The methods described aim at solving the tension between unification of data sets and vocabularies on the one hand and maximum openness for the integration of future resources and adaption of external information on the other hand.
%U https://aclanthology.org/2020.lrec-1.354
%P 2901-2905
Markdown (Informal)
[Towards Flexible Cross-Resource Exploitation of Heterogeneous Language Documentation Data](https://aclanthology.org/2020.lrec-1.354) (Jettka & Lehmberg, LREC 2020)
ACL