@inproceedings{hasan-etal-2021-hitting,
title = "Hitting your {MARQ}: Multimodal {AR}gument Quality Assessment in Long Debate Video",
author = "Hasan, Md Kamrul and
Spann, James and
Hasan, Masum and
Islam, Md Saiful and
Haut, Kurtis and
Mihalcea, Rada and
Hoque, Ehsan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.515",
doi = "10.18653/v1/2021.emnlp-main.515",
pages = "6387--6397",
abstract = "The combination of gestures, intonations, and textual content plays a key role in argument delivery. However, the current literature mostly considers textual content while assessing the quality of an argument, and it is limited to datasets containing short sequences (18-48 words). In this paper, we study argument quality assessment in a multimodal context, and experiment on DBATES, a publicly available dataset of long debate videos. First, we propose a set of interpretable debate centric features such as clarity, content variation, body movement cues, and pauses, inspired by theories of argumentation quality. Second, we design the Multimodal ARgument Quality assessor (MARQ) {--} a hierarchical neural network model that summarizes the multimodal signals on long sequences and enriches the multimodal embedding with debate centric features. Our proposed MARQ model achieves an accuracy of 81.91{\%} on the argument quality prediction task and outperforms established baseline models with an error rate reduction of 22.7{\%}. Through ablation studies, we demonstrate the importance of multimodal cues in modeling argument quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-etal-2021-hitting">
<titleInfo>
<title>Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate Video</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Kamrul</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Spann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masum</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Saiful</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kurtis</namePart>
<namePart type="family">Haut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The combination of gestures, intonations, and textual content plays a key role in argument delivery. However, the current literature mostly considers textual content while assessing the quality of an argument, and it is limited to datasets containing short sequences (18-48 words). In this paper, we study argument quality assessment in a multimodal context, and experiment on DBATES, a publicly available dataset of long debate videos. First, we propose a set of interpretable debate centric features such as clarity, content variation, body movement cues, and pauses, inspired by theories of argumentation quality. Second, we design the Multimodal ARgument Quality assessor (MARQ) – a hierarchical neural network model that summarizes the multimodal signals on long sequences and enriches the multimodal embedding with debate centric features. Our proposed MARQ model achieves an accuracy of 81.91% on the argument quality prediction task and outperforms established baseline models with an error rate reduction of 22.7%. Through ablation studies, we demonstrate the importance of multimodal cues in modeling argument quality.</abstract>
<identifier type="citekey">hasan-etal-2021-hitting</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.515</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.515</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>6387</start>
<end>6397</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate Video
%A Hasan, Md Kamrul
%A Spann, James
%A Hasan, Masum
%A Islam, Md Saiful
%A Haut, Kurtis
%A Mihalcea, Rada
%A Hoque, Ehsan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F hasan-etal-2021-hitting
%X The combination of gestures, intonations, and textual content plays a key role in argument delivery. However, the current literature mostly considers textual content while assessing the quality of an argument, and it is limited to datasets containing short sequences (18-48 words). In this paper, we study argument quality assessment in a multimodal context, and experiment on DBATES, a publicly available dataset of long debate videos. First, we propose a set of interpretable debate centric features such as clarity, content variation, body movement cues, and pauses, inspired by theories of argumentation quality. Second, we design the Multimodal ARgument Quality assessor (MARQ) – a hierarchical neural network model that summarizes the multimodal signals on long sequences and enriches the multimodal embedding with debate centric features. Our proposed MARQ model achieves an accuracy of 81.91% on the argument quality prediction task and outperforms established baseline models with an error rate reduction of 22.7%. Through ablation studies, we demonstrate the importance of multimodal cues in modeling argument quality.
%R 10.18653/v1/2021.emnlp-main.515
%U https://aclanthology.org/2021.emnlp-main.515
%U https://doi.org/10.18653/v1/2021.emnlp-main.515
%P 6387-6397
Markdown (Informal)
[Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate Video](https://aclanthology.org/2021.emnlp-main.515) (Hasan et al., EMNLP 2021)
ACL