@inproceedings{bagher-zadeh-etal-2020-cmu,
title = "{CMU}-{MOSEAS}: A Multimodal Language Dataset for {S}panish, {P}ortuguese, {G}erman and {F}rench",
author = "Bagher Zadeh, AmirAli and
Cao, Yansheng and
Hessner, Simon and
Liang, Paul Pu and
Poria, Soujanya and
Morency, Louis-Philippe",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.141/",
doi = "10.18653/v1/2020.emnlp-main.141",
pages = "1801--1812",
abstract = "Modeling multimodal language is a core research area in natural language processing. While languages such as English have relatively large multimodal language resources, other widely spoken languages across the globe have few or no large-scale datasets in this area. This disproportionately affects native speakers of languages other than English. As a step towards building more equitable and inclusive multimodal systems, we introduce the first large-scale multimodal language dataset for Spanish, Portuguese, German and French. The proposed dataset, called CMU-MOSEAS (CMU Multimodal Opinion Sentiment, Emotions and Attributes), is the largest of its kind with 40,000 total labelled sentences. It covers a diverse set topics and speakers, and carries supervision of 20 labels including sentiment (and subjectivity), emotions, and attributes. Our evaluations on a state-of-the-art multimodal model demonstrates that CMU-MOSEAS enables further research for multilingual studies in multimodal language."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bagher-zadeh-etal-2020-cmu">
<titleInfo>
<title>CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French</title>
</titleInfo>
<name type="personal">
<namePart type="given">AmirAli</namePart>
<namePart type="family">Bagher Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yansheng</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Hessner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</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">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Modeling multimodal language is a core research area in natural language processing. While languages such as English have relatively large multimodal language resources, other widely spoken languages across the globe have few or no large-scale datasets in this area. This disproportionately affects native speakers of languages other than English. As a step towards building more equitable and inclusive multimodal systems, we introduce the first large-scale multimodal language dataset for Spanish, Portuguese, German and French. The proposed dataset, called CMU-MOSEAS (CMU Multimodal Opinion Sentiment, Emotions and Attributes), is the largest of its kind with 40,000 total labelled sentences. It covers a diverse set topics and speakers, and carries supervision of 20 labels including sentiment (and subjectivity), emotions, and attributes. Our evaluations on a state-of-the-art multimodal model demonstrates that CMU-MOSEAS enables further research for multilingual studies in multimodal language.</abstract>
<identifier type="citekey">bagher-zadeh-etal-2020-cmu</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.141</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.141/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1801</start>
<end>1812</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French
%A Bagher Zadeh, AmirAli
%A Cao, Yansheng
%A Hessner, Simon
%A Liang, Paul Pu
%A Poria, Soujanya
%A Morency, Louis-Philippe
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F bagher-zadeh-etal-2020-cmu
%X Modeling multimodal language is a core research area in natural language processing. While languages such as English have relatively large multimodal language resources, other widely spoken languages across the globe have few or no large-scale datasets in this area. This disproportionately affects native speakers of languages other than English. As a step towards building more equitable and inclusive multimodal systems, we introduce the first large-scale multimodal language dataset for Spanish, Portuguese, German and French. The proposed dataset, called CMU-MOSEAS (CMU Multimodal Opinion Sentiment, Emotions and Attributes), is the largest of its kind with 40,000 total labelled sentences. It covers a diverse set topics and speakers, and carries supervision of 20 labels including sentiment (and subjectivity), emotions, and attributes. Our evaluations on a state-of-the-art multimodal model demonstrates that CMU-MOSEAS enables further research for multilingual studies in multimodal language.
%R 10.18653/v1/2020.emnlp-main.141
%U https://aclanthology.org/2020.emnlp-main.141/
%U https://doi.org/10.18653/v1/2020.emnlp-main.141
%P 1801-1812
Markdown (Informal)
[CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French](https://aclanthology.org/2020.emnlp-main.141/) (Bagher Zadeh et al., EMNLP 2020)
ACL