@inproceedings{rajda-etal-2022-assessment,
title = "Assessment of Massively Multilingual Sentiment Classifiers",
author = "Rajda, Krzysztof and
Augustyniak, Lukasz and
Gramacki, Piotr and
Gruza, Marcin and
Wo{\'z}niak, Szymon and
Kajdanowicz, Tomasz",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Barriere, Valentin and
Tafreshi, Shabnam and
Alqahtani, Sawsan and
Sedoc, Jo{\~a}o and
Klinger, Roman and
Balahur, Alexandra",
booktitle = "Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment {\&} Social Media Analysis",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wassa-1.13",
doi = "10.18653/v1/2022.wassa-1.13",
pages = "125--140",
abstract = "Models are increasing in size and complexity in the hunt for SOTA. But what if those 2{\%}increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets. We deeply evaluate multiple setups, including fine-tuning transformer-based models for measuring performance. We compare results in numerous dimensions addressing the imbalance in both languages coverage and dataset sizes. Finally, we present some best practices for working with such a massive collection of datasets and models for a multi-lingual perspective.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajda-etal-2022-assessment">
<titleInfo>
<title>Assessment of Massively Multilingual Sentiment Classifiers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krzysztof</namePart>
<namePart type="family">Rajda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukasz</namePart>
<namePart type="family">Augustyniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Gramacki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Gruza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Szymon</namePart>
<namePart type="family">Woźniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Kajdanowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Models are increasing in size and complexity in the hunt for SOTA. But what if those 2%increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets. We deeply evaluate multiple setups, including fine-tuning transformer-based models for measuring performance. We compare results in numerous dimensions addressing the imbalance in both languages coverage and dataset sizes. Finally, we present some best practices for working with such a massive collection of datasets and models for a multi-lingual perspective.</abstract>
<identifier type="citekey">rajda-etal-2022-assessment</identifier>
<identifier type="doi">10.18653/v1/2022.wassa-1.13</identifier>
<location>
<url>https://aclanthology.org/2022.wassa-1.13</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>125</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessment of Massively Multilingual Sentiment Classifiers
%A Rajda, Krzysztof
%A Augustyniak, Lukasz
%A Gramacki, Piotr
%A Gruza, Marcin
%A Woźniak, Szymon
%A Kajdanowicz, Tomasz
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Alqahtani, Sawsan
%Y Sedoc, João
%Y Klinger, Roman
%Y Balahur, Alexandra
%S Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F rajda-etal-2022-assessment
%X Models are increasing in size and complexity in the hunt for SOTA. But what if those 2%increase in performance does not make a difference in a production use case? Maybe benefits from a smaller, faster model outweigh those slight performance gains. Also, equally good performance across languages in multilingual tasks is more important than SOTA results on a single one. We present the biggest, unified, multilingual collection of sentiment analysis datasets. We use these to assess 11 models and 80 high-quality sentiment datasets (out of 342 raw datasets collected) in 27 languages and included results on the internally annotated datasets. We deeply evaluate multiple setups, including fine-tuning transformer-based models for measuring performance. We compare results in numerous dimensions addressing the imbalance in both languages coverage and dataset sizes. Finally, we present some best practices for working with such a massive collection of datasets and models for a multi-lingual perspective.
%R 10.18653/v1/2022.wassa-1.13
%U https://aclanthology.org/2022.wassa-1.13
%U https://doi.org/10.18653/v1/2022.wassa-1.13
%P 125-140
Markdown (Informal)
[Assessment of Massively Multilingual Sentiment Classifiers](https://aclanthology.org/2022.wassa-1.13) (Rajda et al., WASSA 2022)
ACL
- Krzysztof Rajda, Lukasz Augustyniak, Piotr Gramacki, Marcin Gruza, Szymon Woźniak, and Tomasz Kajdanowicz. 2022. Assessment of Massively Multilingual Sentiment Classifiers. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 125–140, Dublin, Ireland. Association for Computational Linguistics.