@inproceedings{saha-etal-2021-towards,
title = "Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in {T}witter",
author = "Saha, Tulika and
Upadhyaya, Apoorva and
Saha, Sriparna and
Bhattacharyya, Pushpak",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.456",
doi = "10.18653/v1/2021.naacl-main.456",
pages = "5727--5737",
abstract = "Speech Act Classification determining the communicative intent of an utterance has been investigated widely over the years as a standalone task. This holds true for discussion in any fora including social media platform such as Twitter. But the emotional state of the tweeter which has a considerable effect on the communication has not received the attention it deserves. Closely related to emotion is sentiment, and understanding of one helps understand the other. In this work, we firstly create a new multi-modal, emotion-TA ({`}TA{'} means tweet act, i.e., speech act in Twitter) dataset called \textit{EmoTA} collected from open-source Twitter dataset. We propose a Dyadic Attention Mechanism (DAM) based multi-modal, adversarial multi-tasking framework. DAM incorporates intra-modal and inter-modal attention to fuse multiple modalities and learns generalized features across all the tasks. Experimental results indicate that the proposed framework boosts the performance of the primary task, i.e., TA classification (TAC) by benefitting from the two secondary tasks, i.e., Sentiment and Emotion Analysis compared to its uni-modal and single task TAC (tweet act classification) variants.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-etal-2021-towards">
<titleInfo>
<title>Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tulika</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorva</namePart>
<namePart type="family">Upadhyaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</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>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speech Act Classification determining the communicative intent of an utterance has been investigated widely over the years as a standalone task. This holds true for discussion in any fora including social media platform such as Twitter. But the emotional state of the tweeter which has a considerable effect on the communication has not received the attention it deserves. Closely related to emotion is sentiment, and understanding of one helps understand the other. In this work, we firstly create a new multi-modal, emotion-TA (‘TA’ means tweet act, i.e., speech act in Twitter) dataset called EmoTA collected from open-source Twitter dataset. We propose a Dyadic Attention Mechanism (DAM) based multi-modal, adversarial multi-tasking framework. DAM incorporates intra-modal and inter-modal attention to fuse multiple modalities and learns generalized features across all the tasks. Experimental results indicate that the proposed framework boosts the performance of the primary task, i.e., TA classification (TAC) by benefitting from the two secondary tasks, i.e., Sentiment and Emotion Analysis compared to its uni-modal and single task TAC (tweet act classification) variants.</abstract>
<identifier type="citekey">saha-etal-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.456</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.456</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5727</start>
<end>5737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter
%A Saha, Tulika
%A Upadhyaya, Apoorva
%A Saha, Sriparna
%A Bhattacharyya, Pushpak
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F saha-etal-2021-towards
%X Speech Act Classification determining the communicative intent of an utterance has been investigated widely over the years as a standalone task. This holds true for discussion in any fora including social media platform such as Twitter. But the emotional state of the tweeter which has a considerable effect on the communication has not received the attention it deserves. Closely related to emotion is sentiment, and understanding of one helps understand the other. In this work, we firstly create a new multi-modal, emotion-TA (‘TA’ means tweet act, i.e., speech act in Twitter) dataset called EmoTA collected from open-source Twitter dataset. We propose a Dyadic Attention Mechanism (DAM) based multi-modal, adversarial multi-tasking framework. DAM incorporates intra-modal and inter-modal attention to fuse multiple modalities and learns generalized features across all the tasks. Experimental results indicate that the proposed framework boosts the performance of the primary task, i.e., TA classification (TAC) by benefitting from the two secondary tasks, i.e., Sentiment and Emotion Analysis compared to its uni-modal and single task TAC (tweet act classification) variants.
%R 10.18653/v1/2021.naacl-main.456
%U https://aclanthology.org/2021.naacl-main.456
%U https://doi.org/10.18653/v1/2021.naacl-main.456
%P 5727-5737
Markdown (Informal)
[Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter](https://aclanthology.org/2021.naacl-main.456) (Saha et al., NAACL 2021)
ACL