@inproceedings{joshi-etal-2022-cogmen,
title = "{COGMEN}: {CO}ntextualized {GNN} based Multimodal Emotion recognitio{N}",
author = "Joshi, Abhinav and
Bhat, Ashwani and
Jain, Ayush and
Singh, Atin and
Modi, Ashutosh",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.306",
doi = "10.18653/v1/2022.naacl-main.306",
pages = "4148--4164",
abstract = "Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person{'}s emotions are influenced by the other speaker{'}s utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multi- modal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the- art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joshi-etal-2022-cogmen">
<titleInfo>
<title>COGMEN: COntextualized GNN based Multimodal Emotion recognitioN</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwani</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atin</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person’s emotions are influenced by the other speaker’s utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multi- modal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the- art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.</abstract>
<identifier type="citekey">joshi-etal-2022-cogmen</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.306</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.306</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4148</start>
<end>4164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COGMEN: COntextualized GNN based Multimodal Emotion recognitioN
%A Joshi, Abhinav
%A Bhat, Ashwani
%A Jain, Ayush
%A Singh, Atin
%A Modi, Ashutosh
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F joshi-etal-2022-cogmen
%X Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person’s emotions are influenced by the other speaker’s utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multi- modal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the- art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.
%R 10.18653/v1/2022.naacl-main.306
%U https://aclanthology.org/2022.naacl-main.306
%U https://doi.org/10.18653/v1/2022.naacl-main.306
%P 4148-4164
Markdown (Informal)
[COGMEN: COntextualized GNN based Multimodal Emotion recognitioN](https://aclanthology.org/2022.naacl-main.306) (Joshi et al., NAACL 2022)
ACL
- Abhinav Joshi, Ashwani Bhat, Ayush Jain, Atin Singh, and Ashutosh Modi. 2022. COGMEN: COntextualized GNN based Multimodal Emotion recognitioN. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4148–4164, Seattle, United States. Association for Computational Linguistics.