@inproceedings{cheng-etal-2023-learning,
title = "Learning Multimodal Cues of Children{'}s Uncertainty",
author = "Cheng, Qi and
Inan, Mert and
Mbarki, Rahma and
Grmek, Grace and
Choi, Theresa and
Sun, Yiming and
Persaud, Kimele and
Wang, Jenny and
Alikhani, Malihe",
editor = "Stoyanchev, Svetlana and
Joty, Shafiq and
Schlangen, David and
Dusek, Ondrej and
Kennington, Casey and
Alikhani, Malihe",
booktitle = "Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2023",
address = "Prague, Czechia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigdial-1.41",
doi = "10.18653/v1/2023.sigdial-1.41",
pages = "433--443",
abstract = "Understanding uncertainty plays a critical role in achieving common ground (Clark et al., 1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging concept. In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty. We then present an analysis of the data, studying different roles of uncertainty and its relationship with task difficulty and performance. Lastly, we present a multimodal machine learning model that can predict uncertainty given a real-time video clip of a participant, which we find improves upon a baseline multimodal transformer model. This work informs research on cognitive coordination between human-human and human-AI and has broad implications for gesture understanding and generation. The anonymized version of our data and code will be publicly available upon the completion of the required consent forms and data sheets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2023-learning">
<titleInfo>
<title>Learning Multimodal Cues of Children’s Uncertainty</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mert</namePart>
<namePart type="family">Inan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahma</namePart>
<namePart type="family">Mbarki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grace</namePart>
<namePart type="family">Grmek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theresa</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kimele</namePart>
<namePart type="family">Persaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenny</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Stoyanchev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Dusek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malihe</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Prague, Czechia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding uncertainty plays a critical role in achieving common ground (Clark et al., 1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging concept. In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty. We then present an analysis of the data, studying different roles of uncertainty and its relationship with task difficulty and performance. Lastly, we present a multimodal machine learning model that can predict uncertainty given a real-time video clip of a participant, which we find improves upon a baseline multimodal transformer model. This work informs research on cognitive coordination between human-human and human-AI and has broad implications for gesture understanding and generation. The anonymized version of our data and code will be publicly available upon the completion of the required consent forms and data sheets.</abstract>
<identifier type="citekey">cheng-etal-2023-learning</identifier>
<identifier type="doi">10.18653/v1/2023.sigdial-1.41</identifier>
<location>
<url>https://aclanthology.org/2023.sigdial-1.41</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>433</start>
<end>443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Multimodal Cues of Children’s Uncertainty
%A Cheng, Qi
%A Inan, Mert
%A Mbarki, Rahma
%A Grmek, Grace
%A Choi, Theresa
%A Sun, Yiming
%A Persaud, Kimele
%A Wang, Jenny
%A Alikhani, Malihe
%Y Stoyanchev, Svetlana
%Y Joty, Shafiq
%Y Schlangen, David
%Y Dusek, Ondrej
%Y Kennington, Casey
%Y Alikhani, Malihe
%S Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2023
%8 September
%I Association for Computational Linguistics
%C Prague, Czechia
%F cheng-etal-2023-learning
%X Understanding uncertainty plays a critical role in achieving common ground (Clark et al., 1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging concept. In this work, for the first time, we present a dataset annotated in collaboration with developmental and cognitive psychologists for the purpose of studying nonverbal cues of uncertainty. We then present an analysis of the data, studying different roles of uncertainty and its relationship with task difficulty and performance. Lastly, we present a multimodal machine learning model that can predict uncertainty given a real-time video clip of a participant, which we find improves upon a baseline multimodal transformer model. This work informs research on cognitive coordination between human-human and human-AI and has broad implications for gesture understanding and generation. The anonymized version of our data and code will be publicly available upon the completion of the required consent forms and data sheets.
%R 10.18653/v1/2023.sigdial-1.41
%U https://aclanthology.org/2023.sigdial-1.41
%U https://doi.org/10.18653/v1/2023.sigdial-1.41
%P 433-443
Markdown (Informal)
[Learning Multimodal Cues of Children’s Uncertainty](https://aclanthology.org/2023.sigdial-1.41) (Cheng et al., SIGDIAL 2023)
ACL
- Qi Cheng, Mert Inan, Rahma Mbarki, Grace Grmek, Theresa Choi, Yiming Sun, Kimele Persaud, Jenny Wang, and Malihe Alikhani. 2023. Learning Multimodal Cues of Children’s Uncertainty. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 433–443, Prague, Czechia. Association for Computational Linguistics.