@inproceedings{agrawal-etal-2024-automatic-coding,
title = "Automatic Coding of Contingency in Child-Caregiver Conversations",
author = "Agrawal, Abhishek and
Nikolaus, Mitja and
Favre, Benoit and
Fourtassi, Abdellah",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.166",
pages = "1856--1870",
abstract = "One of the most important communicative skills children have to learn is to engage in meaningful conversations with people around them. At the heart of this learning lies the mastery of contingency, i.e., the ability to contribute to an ongoing exchange in a relevant fashion (e.g., by staying on topic). Current research on this question relies on the manual annotation of a small sample of children, which limits our ability to draw general conclusions about development. Here, we propose to mitigate the limitations of manual labor by relying on automatic tools for contingency judgment in children{'}s early natural interactions with caregivers. Drawing inspiration from the field of dialogue systems evaluation, we built and compared several automatic classifiers. We found that a Transformer-based pre-trained language model {--} when fine-tuned on a relatively small set of data we annotated manually (around 3,500 turns) {--} provided the best predictions. We used this model to automatically annotate, new and large-scale data, almost two orders of magnitude larger than our fine-tuning set. It was able to replicate existing results and generate new data-driven hypotheses. The broad impact of the work is to provide resources that can help the language development community study communicative development at scale, leading to more robust theories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrawal-etal-2024-automatic-coding">
<titleInfo>
<title>Automatic Coding of Contingency in Child-Caregiver Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitja</namePart>
<namePart type="family">Nikolaus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benoit</namePart>
<namePart type="family">Favre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">Fourtassi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the most important communicative skills children have to learn is to engage in meaningful conversations with people around them. At the heart of this learning lies the mastery of contingency, i.e., the ability to contribute to an ongoing exchange in a relevant fashion (e.g., by staying on topic). Current research on this question relies on the manual annotation of a small sample of children, which limits our ability to draw general conclusions about development. Here, we propose to mitigate the limitations of manual labor by relying on automatic tools for contingency judgment in children’s early natural interactions with caregivers. Drawing inspiration from the field of dialogue systems evaluation, we built and compared several automatic classifiers. We found that a Transformer-based pre-trained language model – when fine-tuned on a relatively small set of data we annotated manually (around 3,500 turns) – provided the best predictions. We used this model to automatically annotate, new and large-scale data, almost two orders of magnitude larger than our fine-tuning set. It was able to replicate existing results and generate new data-driven hypotheses. The broad impact of the work is to provide resources that can help the language development community study communicative development at scale, leading to more robust theories.</abstract>
<identifier type="citekey">agrawal-etal-2024-automatic-coding</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.166</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1856</start>
<end>1870</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Coding of Contingency in Child-Caregiver Conversations
%A Agrawal, Abhishek
%A Nikolaus, Mitja
%A Favre, Benoit
%A Fourtassi, Abdellah
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F agrawal-etal-2024-automatic-coding
%X One of the most important communicative skills children have to learn is to engage in meaningful conversations with people around them. At the heart of this learning lies the mastery of contingency, i.e., the ability to contribute to an ongoing exchange in a relevant fashion (e.g., by staying on topic). Current research on this question relies on the manual annotation of a small sample of children, which limits our ability to draw general conclusions about development. Here, we propose to mitigate the limitations of manual labor by relying on automatic tools for contingency judgment in children’s early natural interactions with caregivers. Drawing inspiration from the field of dialogue systems evaluation, we built and compared several automatic classifiers. We found that a Transformer-based pre-trained language model – when fine-tuned on a relatively small set of data we annotated manually (around 3,500 turns) – provided the best predictions. We used this model to automatically annotate, new and large-scale data, almost two orders of magnitude larger than our fine-tuning set. It was able to replicate existing results and generate new data-driven hypotheses. The broad impact of the work is to provide resources that can help the language development community study communicative development at scale, leading to more robust theories.
%U https://aclanthology.org/2024.lrec-main.166
%P 1856-1870
Markdown (Informal)
[Automatic Coding of Contingency in Child-Caregiver Conversations](https://aclanthology.org/2024.lrec-main.166) (Agrawal et al., LREC-COLING 2024)
ACL
- Abhishek Agrawal, Mitja Nikolaus, Benoit Favre, and Abdellah Fourtassi. 2024. Automatic Coding of Contingency in Child-Caregiver Conversations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1856–1870, Torino, Italia. ELRA and ICCL.