@inproceedings{yu-etal-2020-ch,
title = "{CH}-{SIMS}: A {C}hinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality",
author = "Yu, Wenmeng and
Xu, Hua and
Meng, Fanyang and
Zhu, Yilin and
Ma, Yixiao and
Wu, Jiele and
Zou, Jiyun and
Yang, Kaicheng",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.343",
doi = "10.18653/v1/2020.acl-main.343",
pages = "3718--3727",
abstract = "Previous studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations. However, the unified annotations do not always reflect the independent sentiment of single modalities and limit the model to capture the difference between modalities. In this paper, we introduce a Chinese single- and multi-modal sentiment analysis dataset, CH-SIMS, which contains 2,281 refined video segments in the wild with both multimodal and independent unimodal annotations. It allows researchers to study the interaction between modalities or use independent unimodal annotations for unimodal sentiment analysis.Furthermore, we propose a multi-task learning framework based on late fusion as the baseline. Extensive experiments on the CH-SIMS show that our methods achieve state-of-the-art performance and learn more distinctive unimodal representations. The full dataset and codes are available for use at https://github.com/thuiar/MMSA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2020-ch">
<titleInfo>
<title>CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenmeng</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanyang</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilin</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixiao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiele</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiyun</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaicheng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations. However, the unified annotations do not always reflect the independent sentiment of single modalities and limit the model to capture the difference between modalities. In this paper, we introduce a Chinese single- and multi-modal sentiment analysis dataset, CH-SIMS, which contains 2,281 refined video segments in the wild with both multimodal and independent unimodal annotations. It allows researchers to study the interaction between modalities or use independent unimodal annotations for unimodal sentiment analysis.Furthermore, we propose a multi-task learning framework based on late fusion as the baseline. Extensive experiments on the CH-SIMS show that our methods achieve state-of-the-art performance and learn more distinctive unimodal representations. The full dataset and codes are available for use at https://github.com/thuiar/MMSA.</abstract>
<identifier type="citekey">yu-etal-2020-ch</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.343</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.343</url>
</location>
<part>
<date>2020-jul</date>
<extent unit="page">
<start>3718</start>
<end>3727</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality
%A Yu, Wenmeng
%A Xu, Hua
%A Meng, Fanyang
%A Zhu, Yilin
%A Ma, Yixiao
%A Wu, Jiele
%A Zou, Jiyun
%A Yang, Kaicheng
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F yu-etal-2020-ch
%X Previous studies in multimodal sentiment analysis have used limited datasets, which only contain unified multimodal annotations. However, the unified annotations do not always reflect the independent sentiment of single modalities and limit the model to capture the difference between modalities. In this paper, we introduce a Chinese single- and multi-modal sentiment analysis dataset, CH-SIMS, which contains 2,281 refined video segments in the wild with both multimodal and independent unimodal annotations. It allows researchers to study the interaction between modalities or use independent unimodal annotations for unimodal sentiment analysis.Furthermore, we propose a multi-task learning framework based on late fusion as the baseline. Extensive experiments on the CH-SIMS show that our methods achieve state-of-the-art performance and learn more distinctive unimodal representations. The full dataset and codes are available for use at https://github.com/thuiar/MMSA.
%R 10.18653/v1/2020.acl-main.343
%U https://aclanthology.org/2020.acl-main.343
%U https://doi.org/10.18653/v1/2020.acl-main.343
%P 3718-3727
Markdown (Informal)
[CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality](https://aclanthology.org/2020.acl-main.343) (Yu et al., ACL 2020)
ACL