@inproceedings{havaldar-etal-2023-multilingual,
title = "Multilingual Language Models are not Multicultural: A Case Study in Emotion",
author = "Havaldar, Shreya and
Singhal, Bhumika and
Rai, Sunny and
Liu, Langchen and
Guntuku, Sharath Chandra and
Ungar, Lyle",
booktitle = "Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wassa-1.19",
doi = "10.18653/v1/2023.wassa-1.19",
pages = "202--214",
abstract = "Emotions are experienced and expressed differently across the world. In order to use Large Language Models (LMs) for multilingual tasks that require emotional sensitivity, LMs must reflect this cultural variation in emotion. In this study, we investigate whether the widely-used multilingual LMs in 2023 reflect differences in emotional expressions across cultures and languages. We find that embeddings obtained from LMs (e.g., XLM-RoBERTa) are Anglocentric, and generative LMs (e.g., ChatGPT) reflect Western norms, even when responding to prompts in other languages. Our results show that multilingual LMs do not successfully learn the culturally appropriate nuances of emotion and we highlight possible research directions towards correcting this.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="havaldar-etal-2023-multilingual">
<titleInfo>
<title>Multilingual Language Models are not Multicultural: A Case Study in Emotion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Havaldar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhumika</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunny</namePart>
<namePart type="family">Rai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Langchen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharath</namePart>
<namePart type="given">Chandra</namePart>
<namePart type="family">Guntuku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</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 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotions are experienced and expressed differently across the world. In order to use Large Language Models (LMs) for multilingual tasks that require emotional sensitivity, LMs must reflect this cultural variation in emotion. In this study, we investigate whether the widely-used multilingual LMs in 2023 reflect differences in emotional expressions across cultures and languages. We find that embeddings obtained from LMs (e.g., XLM-RoBERTa) are Anglocentric, and generative LMs (e.g., ChatGPT) reflect Western norms, even when responding to prompts in other languages. Our results show that multilingual LMs do not successfully learn the culturally appropriate nuances of emotion and we highlight possible research directions towards correcting this.</abstract>
<identifier type="citekey">havaldar-etal-2023-multilingual</identifier>
<identifier type="doi">10.18653/v1/2023.wassa-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.wassa-1.19</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>202</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multilingual Language Models are not Multicultural: A Case Study in Emotion
%A Havaldar, Shreya
%A Singhal, Bhumika
%A Rai, Sunny
%A Liu, Langchen
%A Guntuku, Sharath Chandra
%A Ungar, Lyle
%S Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F havaldar-etal-2023-multilingual
%X Emotions are experienced and expressed differently across the world. In order to use Large Language Models (LMs) for multilingual tasks that require emotional sensitivity, LMs must reflect this cultural variation in emotion. In this study, we investigate whether the widely-used multilingual LMs in 2023 reflect differences in emotional expressions across cultures and languages. We find that embeddings obtained from LMs (e.g., XLM-RoBERTa) are Anglocentric, and generative LMs (e.g., ChatGPT) reflect Western norms, even when responding to prompts in other languages. Our results show that multilingual LMs do not successfully learn the culturally appropriate nuances of emotion and we highlight possible research directions towards correcting this.
%R 10.18653/v1/2023.wassa-1.19
%U https://aclanthology.org/2023.wassa-1.19
%U https://doi.org/10.18653/v1/2023.wassa-1.19
%P 202-214
Markdown (Informal)
[Multilingual Language Models are not Multicultural: A Case Study in Emotion](https://aclanthology.org/2023.wassa-1.19) (Havaldar et al., WASSA 2023)
ACL
- Shreya Havaldar, Bhumika Singhal, Sunny Rai, Langchen Liu, Sharath Chandra Guntuku, and Lyle Ungar. 2023. Multilingual Language Models are not Multicultural: A Case Study in Emotion. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 202–214, Toronto, Canada. Association for Computational Linguistics.