@inproceedings{qian-etal-2023-sentiment,
title = "Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis",
author = "Qian, Fan and
Han, Jiqing and
He, Yongjun and
Zheng, Tieran and
Zheng, Guibin",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.821",
doi = "10.18653/v1/2023.findings-acl.821",
pages = "12966--12978",
abstract = "Multimodal Sentiment Analysis (MSA) has made great progress that benefits from extraordinary fusion scheme. However, there is a lack of labeled data, resulting in severe overfitting and poor generalization for supervised models applied in this field. In this paper, we propose Sentiment Knowledge Enhanced Self-supervised Learning (SKESL) to capture common sentimental patterns in unlabeled videos, which facilitates further learning on limited labeled data. Specifically, with the help of sentiment knowledge and non-verbal behavior, SKESL conducts sentiment word masking and predicts fine-grained word sentiment intensity, so as to embed sentiment information at the word level into pre-trained multimodal representation. In addition, a non-verbal injection method is also proposed to integrate non-verbal information into the word semantics. Experiments on two standard benchmarks of MSA clearly show that SKESL significantly outperforms the baseline, and achieves new State-Of-The-Art (SOTA) results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qian-etal-2023-sentiment">
<titleInfo>
<title>Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiqing</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjun</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tieran</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guibin</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multimodal Sentiment Analysis (MSA) has made great progress that benefits from extraordinary fusion scheme. However, there is a lack of labeled data, resulting in severe overfitting and poor generalization for supervised models applied in this field. In this paper, we propose Sentiment Knowledge Enhanced Self-supervised Learning (SKESL) to capture common sentimental patterns in unlabeled videos, which facilitates further learning on limited labeled data. Specifically, with the help of sentiment knowledge and non-verbal behavior, SKESL conducts sentiment word masking and predicts fine-grained word sentiment intensity, so as to embed sentiment information at the word level into pre-trained multimodal representation. In addition, a non-verbal injection method is also proposed to integrate non-verbal information into the word semantics. Experiments on two standard benchmarks of MSA clearly show that SKESL significantly outperforms the baseline, and achieves new State-Of-The-Art (SOTA) results.</abstract>
<identifier type="citekey">qian-etal-2023-sentiment</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.821</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.821</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>12966</start>
<end>12978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis
%A Qian, Fan
%A Han, Jiqing
%A He, Yongjun
%A Zheng, Tieran
%A Zheng, Guibin
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F qian-etal-2023-sentiment
%X Multimodal Sentiment Analysis (MSA) has made great progress that benefits from extraordinary fusion scheme. However, there is a lack of labeled data, resulting in severe overfitting and poor generalization for supervised models applied in this field. In this paper, we propose Sentiment Knowledge Enhanced Self-supervised Learning (SKESL) to capture common sentimental patterns in unlabeled videos, which facilitates further learning on limited labeled data. Specifically, with the help of sentiment knowledge and non-verbal behavior, SKESL conducts sentiment word masking and predicts fine-grained word sentiment intensity, so as to embed sentiment information at the word level into pre-trained multimodal representation. In addition, a non-verbal injection method is also proposed to integrate non-verbal information into the word semantics. Experiments on two standard benchmarks of MSA clearly show that SKESL significantly outperforms the baseline, and achieves new State-Of-The-Art (SOTA) results.
%R 10.18653/v1/2023.findings-acl.821
%U https://aclanthology.org/2023.findings-acl.821
%U https://doi.org/10.18653/v1/2023.findings-acl.821
%P 12966-12978
Markdown (Informal)
[Sentiment Knowledge Enhanced Self-supervised Learning for Multimodal Sentiment Analysis](https://aclanthology.org/2023.findings-acl.821) (Qian et al., Findings 2023)
ACL