@inproceedings{zeng-etal-2021-making-contribution,
title = "Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis",
author = "Zeng, Ying and
Mai, Sijie and
Hu, Haifeng",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.109",
doi = "10.18653/v1/2021.findings-emnlp.109",
pages = "1262--1274",
abstract = "Multimodal sentiment analysis (MSA) draws increasing attention with the availability of multimodal data. The boost in performance of MSA models is mainly hindered by two problems. On the one hand, recent MSA works mostly focus on learning cross-modal dynamics, but neglect to explore an optimal solution for unimodal networks, which determines the lower limit of MSA models. On the other hand, noisy information hidden in each modality interferes the learning of correct cross-modal dynamics. To address the above-mentioned problems, we propose a novel MSA framework Modulation Model for Multimodal Sentiment Analysis (M3SA) to identify the contribution of modalities and reduce the impact of noisy information, so as to better learn unimodal and cross-modal dynamics. Specifically, modulation loss is designed to modulate the loss contribution based on the confidence of individual modalities in each utterance, so as to explore an optimal update solution for each unimodal network. Besides, contrary to most existing works which fail to explicitly filter out noisy information, we devise a modality filter module to identify and filter out modality noise for the learning of correct cross-modal embedding. Extensive experiments on publicly datasets demonstrate that our approach achieves state-of-the-art performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2021-making-contribution">
<titleInfo>
<title>Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sijie</namePart>
<namePart type="family">Mai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haifeng</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal sentiment analysis (MSA) draws increasing attention with the availability of multimodal data. The boost in performance of MSA models is mainly hindered by two problems. On the one hand, recent MSA works mostly focus on learning cross-modal dynamics, but neglect to explore an optimal solution for unimodal networks, which determines the lower limit of MSA models. On the other hand, noisy information hidden in each modality interferes the learning of correct cross-modal dynamics. To address the above-mentioned problems, we propose a novel MSA framework Modulation Model for Multimodal Sentiment Analysis (M3SA) to identify the contribution of modalities and reduce the impact of noisy information, so as to better learn unimodal and cross-modal dynamics. Specifically, modulation loss is designed to modulate the loss contribution based on the confidence of individual modalities in each utterance, so as to explore an optimal update solution for each unimodal network. Besides, contrary to most existing works which fail to explicitly filter out noisy information, we devise a modality filter module to identify and filter out modality noise for the learning of correct cross-modal embedding. Extensive experiments on publicly datasets demonstrate that our approach achieves state-of-the-art performance.</abstract>
<identifier type="citekey">zeng-etal-2021-making-contribution</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.109</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.109</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1262</start>
<end>1274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis
%A Zeng, Ying
%A Mai, Sijie
%A Hu, Haifeng
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zeng-etal-2021-making-contribution
%X Multimodal sentiment analysis (MSA) draws increasing attention with the availability of multimodal data. The boost in performance of MSA models is mainly hindered by two problems. On the one hand, recent MSA works mostly focus on learning cross-modal dynamics, but neglect to explore an optimal solution for unimodal networks, which determines the lower limit of MSA models. On the other hand, noisy information hidden in each modality interferes the learning of correct cross-modal dynamics. To address the above-mentioned problems, we propose a novel MSA framework Modulation Model for Multimodal Sentiment Analysis (M3SA) to identify the contribution of modalities and reduce the impact of noisy information, so as to better learn unimodal and cross-modal dynamics. Specifically, modulation loss is designed to modulate the loss contribution based on the confidence of individual modalities in each utterance, so as to explore an optimal update solution for each unimodal network. Besides, contrary to most existing works which fail to explicitly filter out noisy information, we devise a modality filter module to identify and filter out modality noise for the learning of correct cross-modal embedding. Extensive experiments on publicly datasets demonstrate that our approach achieves state-of-the-art performance.
%R 10.18653/v1/2021.findings-emnlp.109
%U https://aclanthology.org/2021.findings-emnlp.109
%U https://doi.org/10.18653/v1/2021.findings-emnlp.109
%P 1262-1274
Markdown (Informal)
[Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis](https://aclanthology.org/2021.findings-emnlp.109) (Zeng et al., Findings 2021)
ACL