@inproceedings{tatariya-etal-2023-transfer,
title = "Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter?",
author = "Tatariya, Kushal and
Lent, Heather and
de Lhoneux, Miryam",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Klinger, Roman",
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-1.32",
doi = "10.18653/v1/2023.wassa-1.32",
pages = "365--378",
abstract = "Monolinguals make up a minority of the world{'}s speakers, and yet most language technologies lag behind in handling linguistic behaviours produced by bilingual and multilingual speakers. A commonly observed phenomenon in such communities is code-mixing, which is prevalent on social media, and thus requires attention in NLP research. In this work, we look into the ability of pretrained language models to handle code-mixed data, with a focus on the impact of languages present in pretraining on the downstream performance of the model as measured on the task of sentiment analysis. Ultimately, we find that the pretraining language has little effect on performance when the model sees code-mixed data during downstream finetuning. We also evaluate the models on code-mixed data in a zero-shot setting, after task-specific finetuning on a monolingual dataset. We find that this brings out differences in model performance that can be attributed to the pretraining languages. We present a thorough analysis of these findings that also looks at model performance based on the composition of participating languages in the code-mixed datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tatariya-etal-2023-transfer">
<titleInfo>
<title>Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Tatariya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heather</namePart>
<namePart type="family">Lent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miryam</namePart>
<namePart type="family">de Lhoneux</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>
<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">Roman</namePart>
<namePart type="family">Klinger</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>Monolinguals make up a minority of the world’s speakers, and yet most language technologies lag behind in handling linguistic behaviours produced by bilingual and multilingual speakers. A commonly observed phenomenon in such communities is code-mixing, which is prevalent on social media, and thus requires attention in NLP research. In this work, we look into the ability of pretrained language models to handle code-mixed data, with a focus on the impact of languages present in pretraining on the downstream performance of the model as measured on the task of sentiment analysis. Ultimately, we find that the pretraining language has little effect on performance when the model sees code-mixed data during downstream finetuning. We also evaluate the models on code-mixed data in a zero-shot setting, after task-specific finetuning on a monolingual dataset. We find that this brings out differences in model performance that can be attributed to the pretraining languages. We present a thorough analysis of these findings that also looks at model performance based on the composition of participating languages in the code-mixed datasets.</abstract>
<identifier type="citekey">tatariya-etal-2023-transfer</identifier>
<identifier type="doi">10.18653/v1/2023.wassa-1.32</identifier>
<location>
<url>https://aclanthology.org/2023.wassa-1.32</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>365</start>
<end>378</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter?
%A Tatariya, Kushal
%A Lent, Heather
%A de Lhoneux, Miryam
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Klinger, Roman
%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 tatariya-etal-2023-transfer
%X Monolinguals make up a minority of the world’s speakers, and yet most language technologies lag behind in handling linguistic behaviours produced by bilingual and multilingual speakers. A commonly observed phenomenon in such communities is code-mixing, which is prevalent on social media, and thus requires attention in NLP research. In this work, we look into the ability of pretrained language models to handle code-mixed data, with a focus on the impact of languages present in pretraining on the downstream performance of the model as measured on the task of sentiment analysis. Ultimately, we find that the pretraining language has little effect on performance when the model sees code-mixed data during downstream finetuning. We also evaluate the models on code-mixed data in a zero-shot setting, after task-specific finetuning on a monolingual dataset. We find that this brings out differences in model performance that can be attributed to the pretraining languages. We present a thorough analysis of these findings that also looks at model performance based on the composition of participating languages in the code-mixed datasets.
%R 10.18653/v1/2023.wassa-1.32
%U https://aclanthology.org/2023.wassa-1.32
%U https://doi.org/10.18653/v1/2023.wassa-1.32
%P 365-378
Markdown (Informal)
[Transfer Learning for Code-Mixed Data: Do Pretraining Languages Matter?](https://aclanthology.org/2023.wassa-1.32) (Tatariya et al., WASSA 2023)
ACL