@inproceedings{dufraisse-etal-2023-mad,
title = "{MAD}-{TSC}: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification",
author = "Dufraisse, Evan and
Popescu, Adrian and
Tourille, Julien and
Brun, Armelle and
Deshayes, Jerome",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.461",
doi = "10.18653/v1/2023.acl-long.461",
pages = "8286--8305",
abstract = "Target-dependent sentiment classification (TSC) enables a fine-grained automatic analysis of sentiments expressed in texts. Sentiment expression varies depending on the domain, and it is necessary to create domain-specific datasets. While socially important, TSC in the news domain remains relatively understudied. We introduce MAD-TSC, a new dataset which differs substantially from existing resources. First, it includes aligned examples in eight languages to facilitate a comparison of performance for individual languages, and a direct comparison of human and machine translation. Second, the dataset is sampled from a diversified parallel news corpus, and is diversified in terms of news sources and geographic spread of entities. Finally, MAD-TSC is more challenging than existing datasets because its examples are more complex. We exemplify the use of MAD-TSC with comprehensive monolingual and multilingual experiments. The latter show that machine translations can successfully replace manual ones, and that performance for all included languages can match that of English by automatically translating test examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dufraisse-etal-2023-mad">
<titleInfo>
<title>MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Evan</namePart>
<namePart type="family">Dufraisse</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Popescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Tourille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Armelle</namePart>
<namePart type="family">Brun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jerome</namePart>
<namePart type="family">Deshayes</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Target-dependent sentiment classification (TSC) enables a fine-grained automatic analysis of sentiments expressed in texts. Sentiment expression varies depending on the domain, and it is necessary to create domain-specific datasets. While socially important, TSC in the news domain remains relatively understudied. We introduce MAD-TSC, a new dataset which differs substantially from existing resources. First, it includes aligned examples in eight languages to facilitate a comparison of performance for individual languages, and a direct comparison of human and machine translation. Second, the dataset is sampled from a diversified parallel news corpus, and is diversified in terms of news sources and geographic spread of entities. Finally, MAD-TSC is more challenging than existing datasets because its examples are more complex. We exemplify the use of MAD-TSC with comprehensive monolingual and multilingual experiments. The latter show that machine translations can successfully replace manual ones, and that performance for all included languages can match that of English by automatically translating test examples.</abstract>
<identifier type="citekey">dufraisse-etal-2023-mad</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.461</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.461</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8286</start>
<end>8305</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification
%A Dufraisse, Evan
%A Popescu, Adrian
%A Tourille, Julien
%A Brun, Armelle
%A Deshayes, Jerome
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F dufraisse-etal-2023-mad
%X Target-dependent sentiment classification (TSC) enables a fine-grained automatic analysis of sentiments expressed in texts. Sentiment expression varies depending on the domain, and it is necessary to create domain-specific datasets. While socially important, TSC in the news domain remains relatively understudied. We introduce MAD-TSC, a new dataset which differs substantially from existing resources. First, it includes aligned examples in eight languages to facilitate a comparison of performance for individual languages, and a direct comparison of human and machine translation. Second, the dataset is sampled from a diversified parallel news corpus, and is diversified in terms of news sources and geographic spread of entities. Finally, MAD-TSC is more challenging than existing datasets because its examples are more complex. We exemplify the use of MAD-TSC with comprehensive monolingual and multilingual experiments. The latter show that machine translations can successfully replace manual ones, and that performance for all included languages can match that of English by automatically translating test examples.
%R 10.18653/v1/2023.acl-long.461
%U https://aclanthology.org/2023.acl-long.461
%U https://doi.org/10.18653/v1/2023.acl-long.461
%P 8286-8305
Markdown (Informal)
[MAD-TSC: A Multilingual Aligned News Dataset for Target-dependent Sentiment Classification](https://aclanthology.org/2023.acl-long.461) (Dufraisse et al., ACL 2023)
ACL