@inproceedings{kniele-beloucif-2023-uppsala,
title = "{U}ppsala {U}niversity at {S}em{E}val-2023 Task12: Zero-shot Sentiment Classification for {N}igerian {P}idgin Tweets",
author = "Kniele, Annika and
Beloucif, Meriem",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.205",
doi = "10.18653/v1/2023.semeval-1.205",
pages = "1491--1497",
abstract = "While sentiment classification has been considered a practically solved task for high-resource languages such as English, the scarcity of data for many languages still makes it a challenging task. The AfriSenti-SemEval shared task aims to classify sentiment on Twitter data for 14 low-resource African languages. In our participation, we focus on Nigerian Pidgin as the target language. We have investigated the effect of English monolingual and multilingual pre-trained models on the sentiment classification task for Nigerian Pidgin. Our setup includes zero-shot models (using English, Igbo and Hausa data) and a Nigerian Pidgin fine-tuned model. Our results show that English fine-tuned models perform slightly better than models fine-tuned on other Nigerian languages, which could be explained by the lexical and structural closeness between Nigerian Pidgin and English. The best results were reported on the monolingual Nigerian Pidgin data. The model pre-trained on English and fine-tuned on Nigerian Pidgin was submitted to Task A Track 4 of the AfriSenti-SemEval Shared Task 12, and scored 25 out of 32 in the ranking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kniele-beloucif-2023-uppsala">
<titleInfo>
<title>Uppsala University at SemEval-2023 Task12: Zero-shot Sentiment Classification for Nigerian Pidgin Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annika</namePart>
<namePart type="family">Kniele</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meriem</namePart>
<namePart type="family">Beloucif</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 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</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>While sentiment classification has been considered a practically solved task for high-resource languages such as English, the scarcity of data for many languages still makes it a challenging task. The AfriSenti-SemEval shared task aims to classify sentiment on Twitter data for 14 low-resource African languages. In our participation, we focus on Nigerian Pidgin as the target language. We have investigated the effect of English monolingual and multilingual pre-trained models on the sentiment classification task for Nigerian Pidgin. Our setup includes zero-shot models (using English, Igbo and Hausa data) and a Nigerian Pidgin fine-tuned model. Our results show that English fine-tuned models perform slightly better than models fine-tuned on other Nigerian languages, which could be explained by the lexical and structural closeness between Nigerian Pidgin and English. The best results were reported on the monolingual Nigerian Pidgin data. The model pre-trained on English and fine-tuned on Nigerian Pidgin was submitted to Task A Track 4 of the AfriSenti-SemEval Shared Task 12, and scored 25 out of 32 in the ranking.</abstract>
<identifier type="citekey">kniele-beloucif-2023-uppsala</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.205</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.205</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1491</start>
<end>1497</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uppsala University at SemEval-2023 Task12: Zero-shot Sentiment Classification for Nigerian Pidgin Tweets
%A Kniele, Annika
%A Beloucif, Meriem
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F kniele-beloucif-2023-uppsala
%X While sentiment classification has been considered a practically solved task for high-resource languages such as English, the scarcity of data for many languages still makes it a challenging task. The AfriSenti-SemEval shared task aims to classify sentiment on Twitter data for 14 low-resource African languages. In our participation, we focus on Nigerian Pidgin as the target language. We have investigated the effect of English monolingual and multilingual pre-trained models on the sentiment classification task for Nigerian Pidgin. Our setup includes zero-shot models (using English, Igbo and Hausa data) and a Nigerian Pidgin fine-tuned model. Our results show that English fine-tuned models perform slightly better than models fine-tuned on other Nigerian languages, which could be explained by the lexical and structural closeness between Nigerian Pidgin and English. The best results were reported on the monolingual Nigerian Pidgin data. The model pre-trained on English and fine-tuned on Nigerian Pidgin was submitted to Task A Track 4 of the AfriSenti-SemEval Shared Task 12, and scored 25 out of 32 in the ranking.
%R 10.18653/v1/2023.semeval-1.205
%U https://aclanthology.org/2023.semeval-1.205
%U https://doi.org/10.18653/v1/2023.semeval-1.205
%P 1491-1497
Markdown (Informal)
[Uppsala University at SemEval-2023 Task12: Zero-shot Sentiment Classification for Nigerian Pidgin Tweets](https://aclanthology.org/2023.semeval-1.205) (Kniele & Beloucif, SemEval 2023)
ACL