@inproceedings{dingemanse-liesenfeld-2022-text,
title = "From text to talk: {H}arnessing conversational corpora for humane and diversity-aware language technology",
author = "Dingemanse, Mark and
Liesenfeld, Andreas",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.385",
doi = "10.18653/v1/2022.acl-long.385",
pages = "5614--5633",
abstract = "Informal social interaction is the primordial home of human language. Linguistically diverse conversational corpora are an important and largely untapped resource for computational linguistics and language technology. Through the efforts of a worldwide language documentation movement, such corpora are increasingly becoming available. We show how interactional data from 63 languages (26 families) harbours insights about turn-taking, timing, sequential structure and social action, with implications for language technology, natural language understanding, and the design of conversational interfaces. Harnessing linguistically diverse conversational corpora will provide the empirical foundations for flexible, localizable, humane language technologies of the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dingemanse-liesenfeld-2022-text">
<titleInfo>
<title>From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dingemanse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Liesenfeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Informal social interaction is the primordial home of human language. Linguistically diverse conversational corpora are an important and largely untapped resource for computational linguistics and language technology. Through the efforts of a worldwide language documentation movement, such corpora are increasingly becoming available. We show how interactional data from 63 languages (26 families) harbours insights about turn-taking, timing, sequential structure and social action, with implications for language technology, natural language understanding, and the design of conversational interfaces. Harnessing linguistically diverse conversational corpora will provide the empirical foundations for flexible, localizable, humane language technologies of the future.</abstract>
<identifier type="citekey">dingemanse-liesenfeld-2022-text</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.385</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.385</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>5614</start>
<end>5633</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology
%A Dingemanse, Mark
%A Liesenfeld, Andreas
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F dingemanse-liesenfeld-2022-text
%X Informal social interaction is the primordial home of human language. Linguistically diverse conversational corpora are an important and largely untapped resource for computational linguistics and language technology. Through the efforts of a worldwide language documentation movement, such corpora are increasingly becoming available. We show how interactional data from 63 languages (26 families) harbours insights about turn-taking, timing, sequential structure and social action, with implications for language technology, natural language understanding, and the design of conversational interfaces. Harnessing linguistically diverse conversational corpora will provide the empirical foundations for flexible, localizable, humane language technologies of the future.
%R 10.18653/v1/2022.acl-long.385
%U https://aclanthology.org/2022.acl-long.385
%U https://doi.org/10.18653/v1/2022.acl-long.385
%P 5614-5633
Markdown (Informal)
[From text to talk: Harnessing conversational corpora for humane and diversity-aware language technology](https://aclanthology.org/2022.acl-long.385) (Dingemanse & Liesenfeld, ACL 2022)
ACL