@inproceedings{zhang-chai-2021-coin,
title = "{COIN}: Conversational Interactive Networks for Emotion Recognition in Conversation",
author = "Zhang, Haidong and
Chai, Yekun",
editor = "Zadeh, Amir and
Morency, Louis-Philippe and
Liang, Paul Pu and
Ross, Candace and
Salakhutdinov, Ruslan and
Poria, Soujanya and
Cambria, Erik and
Shi, Kelly",
booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.maiworkshop-1.3",
doi = "10.18653/v1/2021.maiworkshop-1.3",
pages = "12--18",
abstract = "Emotion recognition in conversation has received considerable attention recently because of its practical industrial applications. Existing methods tend to overlook the immediate mutual interaction between different speakers in the speaker-utterance level, or apply single speaker-agnostic RNN for utterances from different speakers. We propose COIN, a conversational interactive model to mitigate this problem by applying state mutual interaction within history contexts. In addition, we introduce a stacked global interaction module to capture the contextual and inter-dependency representation in a hierarchical manner. To improve the robustness and generalization during training, we generate adversarial examples by applying the minor perturbations on multimodal feature inputs, unveiling the benefits of adversarial examples for emotion detection. The proposed model empirically achieves the current state-of-the-art results on the IEMOCAP benchmark dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-chai-2021-coin">
<titleInfo>
<title>COIN: Conversational Interactive Networks for Emotion Recognition in Conversation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haidong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yekun</namePart>
<namePart type="family">Chai</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 Third Workshop on Multimodal Artificial Intelligence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">Pu</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Candace</namePart>
<namePart type="family">Ross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Salakhutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion recognition in conversation has received considerable attention recently because of its practical industrial applications. Existing methods tend to overlook the immediate mutual interaction between different speakers in the speaker-utterance level, or apply single speaker-agnostic RNN for utterances from different speakers. We propose COIN, a conversational interactive model to mitigate this problem by applying state mutual interaction within history contexts. In addition, we introduce a stacked global interaction module to capture the contextual and inter-dependency representation in a hierarchical manner. To improve the robustness and generalization during training, we generate adversarial examples by applying the minor perturbations on multimodal feature inputs, unveiling the benefits of adversarial examples for emotion detection. The proposed model empirically achieves the current state-of-the-art results on the IEMOCAP benchmark dataset.</abstract>
<identifier type="citekey">zhang-chai-2021-coin</identifier>
<identifier type="doi">10.18653/v1/2021.maiworkshop-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.maiworkshop-1.3</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>12</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COIN: Conversational Interactive Networks for Emotion Recognition in Conversation
%A Zhang, Haidong
%A Chai, Yekun
%Y Zadeh, Amir
%Y Morency, Louis-Philippe
%Y Liang, Paul Pu
%Y Ross, Candace
%Y Salakhutdinov, Ruslan
%Y Poria, Soujanya
%Y Cambria, Erik
%Y Shi, Kelly
%S Proceedings of the Third Workshop on Multimodal Artificial Intelligence
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhang-chai-2021-coin
%X Emotion recognition in conversation has received considerable attention recently because of its practical industrial applications. Existing methods tend to overlook the immediate mutual interaction between different speakers in the speaker-utterance level, or apply single speaker-agnostic RNN for utterances from different speakers. We propose COIN, a conversational interactive model to mitigate this problem by applying state mutual interaction within history contexts. In addition, we introduce a stacked global interaction module to capture the contextual and inter-dependency representation in a hierarchical manner. To improve the robustness and generalization during training, we generate adversarial examples by applying the minor perturbations on multimodal feature inputs, unveiling the benefits of adversarial examples for emotion detection. The proposed model empirically achieves the current state-of-the-art results on the IEMOCAP benchmark dataset.
%R 10.18653/v1/2021.maiworkshop-1.3
%U https://aclanthology.org/2021.maiworkshop-1.3
%U https://doi.org/10.18653/v1/2021.maiworkshop-1.3
%P 12-18
Markdown (Informal)
[COIN: Conversational Interactive Networks for Emotion Recognition in Conversation](https://aclanthology.org/2021.maiworkshop-1.3) (Zhang & Chai, maiworkshop 2021)
ACL