@inproceedings{cheng-etal-2024-effectiveness,
title = "Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task",
author = "Cheng, Yao-Fei and
Hong, Jeongyeob and
Wang, Andrew and
Silva, Anita and
Levow, Gina-Anne",
editor = "De Clercq, Orph{\'e}e and
Barriere, Valentin and
Barnes, Jeremy and
Klinger, Roman and
Sedoc, Jo{\~a}o and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wassa-1.51",
doi = "10.18653/v1/2024.wassa-1.51",
pages = "511--522",
abstract = "This paper introduces our submitted systems for WASSA 2024 Shared Task 2: Cross-Lingual Emotion Detection. We implemented a BERT-based classifier and an in-context learning-based system. Our best-performing model, using English Chain of Thought prompts with trigger words, reached 3rd overall with an F1 score of 0.6015. Following the motivation of the shared task, we further analyzed the scalability and transferability of the monolingual English dataset on cross-lingual tasks. Our analysis demonstrates the importance of data quality over quantity. We also found that augmented multilingual data does not necessarily perform better than English monolingual data in cross-lingual tasks. We open-sourced the augmented data and source code of our system for future research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2024-effectiveness">
<titleInfo>
<title>Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yao-Fei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeongyeob</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gina-Anne</namePart>
<namePart type="family">Levow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<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">Jeremy</namePart>
<namePart type="family">Barnes</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">João</namePart>
<namePart type="family">Sedoc</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper introduces our submitted systems for WASSA 2024 Shared Task 2: Cross-Lingual Emotion Detection. We implemented a BERT-based classifier and an in-context learning-based system. Our best-performing model, using English Chain of Thought prompts with trigger words, reached 3rd overall with an F1 score of 0.6015. Following the motivation of the shared task, we further analyzed the scalability and transferability of the monolingual English dataset on cross-lingual tasks. Our analysis demonstrates the importance of data quality over quantity. We also found that augmented multilingual data does not necessarily perform better than English monolingual data in cross-lingual tasks. We open-sourced the augmented data and source code of our system for future research.</abstract>
<identifier type="citekey">cheng-etal-2024-effectiveness</identifier>
<identifier type="doi">10.18653/v1/2024.wassa-1.51</identifier>
<location>
<url>https://aclanthology.org/2024.wassa-1.51</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>511</start>
<end>522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task
%A Cheng, Yao-Fei
%A Hong, Jeongyeob
%A Wang, Andrew
%A Silva, Anita
%A Levow, Gina-Anne
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Barnes, Jeremy
%Y Klinger, Roman
%Y Sedoc, João
%Y Tafreshi, Shabnam
%S Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F cheng-etal-2024-effectiveness
%X This paper introduces our submitted systems for WASSA 2024 Shared Task 2: Cross-Lingual Emotion Detection. We implemented a BERT-based classifier and an in-context learning-based system. Our best-performing model, using English Chain of Thought prompts with trigger words, reached 3rd overall with an F1 score of 0.6015. Following the motivation of the shared task, we further analyzed the scalability and transferability of the monolingual English dataset on cross-lingual tasks. Our analysis demonstrates the importance of data quality over quantity. We also found that augmented multilingual data does not necessarily perform better than English monolingual data in cross-lingual tasks. We open-sourced the augmented data and source code of our system for future research.
%R 10.18653/v1/2024.wassa-1.51
%U https://aclanthology.org/2024.wassa-1.51
%U https://doi.org/10.18653/v1/2024.wassa-1.51
%P 511-522
Markdown (Informal)
[Effectiveness of Scalable Monolingual Data and Trigger Words Prompting on Cross-Lingual Emotion Detection Task](https://aclanthology.org/2024.wassa-1.51) (Cheng et al., WASSA-WS 2024)
ACL