@inproceedings{paschen-etal-2020-building,
title = "Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data ({D}o{R}e{C}o)",
author = "Paschen, Ludger and
Delafontaine, Fran{\c{c}}ois and
Draxler, Christoph and
Fuchs, Susanne and
Stave, Matthew and
Seifart, Frank",
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-1.324/",
pages = "2657--2666",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Natural speech data on many languages have been collected by language documentation projects aiming to preserve lingustic and cultural traditions in audivisual records. These data hold great potential for large-scale cross-linguistic research into phonetics and language processing. Major obstacles to utilizing such data for typological studies include the non-homogenous nature of file formats and annotation conventions found both across and within archived collections. Moreover, time-aligned audio transcriptions are typically only available at the level of broad (multi-word) phrases but not at the word and segment levels. We report on solutions developed for these issues within the DoReCo (DOcumentation REference COrpus) project. DoReCo aims at providing time-aligned transcriptions for at least 50 collections of under-resourced languages. This paper gives a preliminary overview of the current state of the project and details our workflow, in particular standardization of formats and conventions, the addition of segmental alignments with WebMAUS, and DoReCo`s applicability for subsequent research programs. By making the data accessible to the scientific community, DoReCo is designed to bridge the gap between language documentation and linguistic inquiry."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paschen-etal-2020-building">
<titleInfo>
<title>Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data (DoReCo)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ludger</namePart>
<namePart type="family">Paschen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Delafontaine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Draxler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susanne</namePart>
<namePart type="family">Fuchs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Stave</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Seifart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>Natural speech data on many languages have been collected by language documentation projects aiming to preserve lingustic and cultural traditions in audivisual records. These data hold great potential for large-scale cross-linguistic research into phonetics and language processing. Major obstacles to utilizing such data for typological studies include the non-homogenous nature of file formats and annotation conventions found both across and within archived collections. Moreover, time-aligned audio transcriptions are typically only available at the level of broad (multi-word) phrases but not at the word and segment levels. We report on solutions developed for these issues within the DoReCo (DOcumentation REference COrpus) project. DoReCo aims at providing time-aligned transcriptions for at least 50 collections of under-resourced languages. This paper gives a preliminary overview of the current state of the project and details our workflow, in particular standardization of formats and conventions, the addition of segmental alignments with WebMAUS, and DoReCo‘s applicability for subsequent research programs. By making the data accessible to the scientific community, DoReCo is designed to bridge the gap between language documentation and linguistic inquiry.</abstract>
<identifier type="citekey">paschen-etal-2020-building</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.324/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2657</start>
<end>2666</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data (DoReCo)
%A Paschen, Ludger
%A Delafontaine, François
%A Draxler, Christoph
%A Fuchs, Susanne
%A Stave, Matthew
%A Seifart, Frank
%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 eng
%F paschen-etal-2020-building
%X Natural speech data on many languages have been collected by language documentation projects aiming to preserve lingustic and cultural traditions in audivisual records. These data hold great potential for large-scale cross-linguistic research into phonetics and language processing. Major obstacles to utilizing such data for typological studies include the non-homogenous nature of file formats and annotation conventions found both across and within archived collections. Moreover, time-aligned audio transcriptions are typically only available at the level of broad (multi-word) phrases but not at the word and segment levels. We report on solutions developed for these issues within the DoReCo (DOcumentation REference COrpus) project. DoReCo aims at providing time-aligned transcriptions for at least 50 collections of under-resourced languages. This paper gives a preliminary overview of the current state of the project and details our workflow, in particular standardization of formats and conventions, the addition of segmental alignments with WebMAUS, and DoReCo‘s applicability for subsequent research programs. By making the data accessible to the scientific community, DoReCo is designed to bridge the gap between language documentation and linguistic inquiry.
%U https://aclanthology.org/2020.lrec-1.324/
%P 2657-2666
Markdown (Informal)
[Building a Time-Aligned Cross-Linguistic Reference Corpus from Language Documentation Data (DoReCo)](https://aclanthology.org/2020.lrec-1.324/) (Paschen et al., LREC 2020)
ACL