@inproceedings{liesenfeld-dingemanse-2022-building,
title = "Building and curating conversational corpora for diversity-aware language science and technology",
author = "Liesenfeld, Andreas and
Dingemanse, Mark",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.126",
pages = "1178--1192",
abstract = "We present an analysis pipeline and best practice guidelines for building and curating corpora of everyday conversation in diverse languages. Surveying language documentation corpora and other resources that cover 67 languages and varieties from 28 phyla, we describe the compilation and curation process, specify minimal properties of a unified format for interactional data, and develop methods for quality control that take into account turn-taking and timing. Two case studies show the broad utility of conversational data for (i) charting human interactional infrastructure and (ii) tracing challenges and opportunities for current ASR solutions. Linguistically diverse conversational corpora can provide new insights for the language sciences and stronger empirical foundations for language technology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liesenfeld-dingemanse-2022-building">
<titleInfo>
<title>Building and curating conversational corpora for diversity-aware language science and technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Liesenfeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dingemanse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>We present an analysis pipeline and best practice guidelines for building and curating corpora of everyday conversation in diverse languages. Surveying language documentation corpora and other resources that cover 67 languages and varieties from 28 phyla, we describe the compilation and curation process, specify minimal properties of a unified format for interactional data, and develop methods for quality control that take into account turn-taking and timing. Two case studies show the broad utility of conversational data for (i) charting human interactional infrastructure and (ii) tracing challenges and opportunities for current ASR solutions. Linguistically diverse conversational corpora can provide new insights for the language sciences and stronger empirical foundations for language technology.</abstract>
<identifier type="citekey">liesenfeld-dingemanse-2022-building</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.126</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1178</start>
<end>1192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building and curating conversational corpora for diversity-aware language science and technology
%A Liesenfeld, Andreas
%A Dingemanse, Mark
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F liesenfeld-dingemanse-2022-building
%X We present an analysis pipeline and best practice guidelines for building and curating corpora of everyday conversation in diverse languages. Surveying language documentation corpora and other resources that cover 67 languages and varieties from 28 phyla, we describe the compilation and curation process, specify minimal properties of a unified format for interactional data, and develop methods for quality control that take into account turn-taking and timing. Two case studies show the broad utility of conversational data for (i) charting human interactional infrastructure and (ii) tracing challenges and opportunities for current ASR solutions. Linguistically diverse conversational corpora can provide new insights for the language sciences and stronger empirical foundations for language technology.
%U https://aclanthology.org/2022.lrec-1.126
%P 1178-1192
Markdown (Informal)
[Building and curating conversational corpora for diversity-aware language science and technology](https://aclanthology.org/2022.lrec-1.126) (Liesenfeld & Dingemanse, LREC 2022)
ACL