@inproceedings{ghosh-etal-2022-comma,
title = "{COMMA}-{DEER}: {CO}mmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations",
author = "Ghosh, Soumitra and
Singh, Gopendra Vikram and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.608",
pages = "6978--6990",
abstract = "Mental health is a critical component of the United Nations{'} Sustainable Development Goals (SDGs), particularly Goal 3, which aims to provide {``}good health and well-being{''}. The present mental health treatment gap is exacerbated by stigma, lack of human resources, and lack of research capability for implementation and policy reform. We present and discuss a novel task of detecting emotional reasoning (ER) and accompanying emotions in conversations. In particular, we create a first-of-its-kind multimodal mental health conversational corpus that is manually annotated at the utterance level with emotional reasoning and related emotion. We develop a multimodal multitask framework with a novel multimodal feature fusion technique and a contextuality learning module to handle the two tasks. Leveraging multimodal sources of information, commonsense reasoning, and through a multitask framework, our proposed model produces strong results. We achieve performance gains of 6{\%} accuracy and 4.62{\%} F1 on the emotion detection task and 3.56{\%} accuracy and 3.31{\%} F1 on the ER detection task, when compared to the existing state-of-the-art model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2022-comma">
<titleInfo>
<title>COMMA-DEER: COmmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumitra</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gopendra</namePart>
<namePart type="given">Vikram</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</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>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Mental health is a critical component of the United Nations’ Sustainable Development Goals (SDGs), particularly Goal 3, which aims to provide “good health and well-being”. The present mental health treatment gap is exacerbated by stigma, lack of human resources, and lack of research capability for implementation and policy reform. We present and discuss a novel task of detecting emotional reasoning (ER) and accompanying emotions in conversations. In particular, we create a first-of-its-kind multimodal mental health conversational corpus that is manually annotated at the utterance level with emotional reasoning and related emotion. We develop a multimodal multitask framework with a novel multimodal feature fusion technique and a contextuality learning module to handle the two tasks. Leveraging multimodal sources of information, commonsense reasoning, and through a multitask framework, our proposed model produces strong results. We achieve performance gains of 6% accuracy and 4.62% F1 on the emotion detection task and 3.56% accuracy and 3.31% F1 on the ER detection task, when compared to the existing state-of-the-art model.</abstract>
<identifier type="citekey">ghosh-etal-2022-comma</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.608</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>6978</start>
<end>6990</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COMMA-DEER: COmmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations
%A Ghosh, Soumitra
%A Singh, Gopendra Vikram
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F ghosh-etal-2022-comma
%X Mental health is a critical component of the United Nations’ Sustainable Development Goals (SDGs), particularly Goal 3, which aims to provide “good health and well-being”. The present mental health treatment gap is exacerbated by stigma, lack of human resources, and lack of research capability for implementation and policy reform. We present and discuss a novel task of detecting emotional reasoning (ER) and accompanying emotions in conversations. In particular, we create a first-of-its-kind multimodal mental health conversational corpus that is manually annotated at the utterance level with emotional reasoning and related emotion. We develop a multimodal multitask framework with a novel multimodal feature fusion technique and a contextuality learning module to handle the two tasks. Leveraging multimodal sources of information, commonsense reasoning, and through a multitask framework, our proposed model produces strong results. We achieve performance gains of 6% accuracy and 4.62% F1 on the emotion detection task and 3.56% accuracy and 3.31% F1 on the ER detection task, when compared to the existing state-of-the-art model.
%U https://aclanthology.org/2022.coling-1.608
%P 6978-6990
Markdown (Informal)
[COMMA-DEER: COmmon-sense Aware Multimodal Multitask Approach for Detection of Emotion and Emotional Reasoning in Conversations](https://aclanthology.org/2022.coling-1.608) (Ghosh et al., COLING 2022)
ACL