@inproceedings{akhtar-etal-2019-multi,
title = "Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis",
author = "Akhtar, Md Shad and
Chauhan, Dushyant and
Ghosal, Deepanway and
Poria, Soujanya and
Ekbal, Asif and
Bhattacharyya, Pushpak",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1034",
doi = "10.18653/v1/N19-1034",
pages = "370--379",
abstract = "Related tasks often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multi-task learning framework that jointly performs sentiment and emotion analysis both. The multi-modal inputs (i.e. text, acoustic and visual frames) of a video convey diverse and distinctive information, and usually do not have equal contribution in the decision making. We propose a context-level inter-modal attention framework for simultaneously predicting the sentiment and expressed emotions of an utterance. We evaluate our proposed approach on CMU-MOSEI dataset for multi-modal sentiment and emotion analysis. Evaluation results suggest that multi-task learning framework offers improvement over the single-task framework. The proposed approach reports new state-of-the-art performance for both sentiment analysis and emotion analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhtar-etal-2019-multi">
<titleInfo>
<title>Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dushyant</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deepanway</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</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>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Related tasks often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multi-task learning framework that jointly performs sentiment and emotion analysis both. The multi-modal inputs (i.e. text, acoustic and visual frames) of a video convey diverse and distinctive information, and usually do not have equal contribution in the decision making. We propose a context-level inter-modal attention framework for simultaneously predicting the sentiment and expressed emotions of an utterance. We evaluate our proposed approach on CMU-MOSEI dataset for multi-modal sentiment and emotion analysis. Evaluation results suggest that multi-task learning framework offers improvement over the single-task framework. The proposed approach reports new state-of-the-art performance for both sentiment analysis and emotion analysis.</abstract>
<identifier type="citekey">akhtar-etal-2019-multi</identifier>
<identifier type="doi">10.18653/v1/N19-1034</identifier>
<location>
<url>https://aclanthology.org/N19-1034</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>370</start>
<end>379</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis
%A Akhtar, Md Shad
%A Chauhan, Dushyant
%A Ghosal, Deepanway
%A Poria, Soujanya
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F akhtar-etal-2019-multi
%X Related tasks often have inter-dependence on each other and perform better when solved in a joint framework. In this paper, we present a deep multi-task learning framework that jointly performs sentiment and emotion analysis both. The multi-modal inputs (i.e. text, acoustic and visual frames) of a video convey diverse and distinctive information, and usually do not have equal contribution in the decision making. We propose a context-level inter-modal attention framework for simultaneously predicting the sentiment and expressed emotions of an utterance. We evaluate our proposed approach on CMU-MOSEI dataset for multi-modal sentiment and emotion analysis. Evaluation results suggest that multi-task learning framework offers improvement over the single-task framework. The proposed approach reports new state-of-the-art performance for both sentiment analysis and emotion analysis.
%R 10.18653/v1/N19-1034
%U https://aclanthology.org/N19-1034
%U https://doi.org/10.18653/v1/N19-1034
%P 370-379
Markdown (Informal)
[Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis](https://aclanthology.org/N19-1034) (Akhtar et al., NAACL 2019)
ACL
- Md Shad Akhtar, Dushyant Chauhan, Deepanway Ghosal, Soujanya Poria, Asif Ekbal, and Pushpak Bhattacharyya. 2019. Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 370–379, Minneapolis, Minnesota. Association for Computational Linguistics.