@inproceedings{nuci-etal-2024-roberta,
title = "{R}o{BERT}a Low Resource Fine Tuning for Sentiment Analysis in {A}lbanian",
author = "Nuci, Krenare Pireva and
Landes, Paul and
Di Eugenio, Barbara",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1233",
pages = "14146--14151",
abstract = "The education domain has been a popular area of collaboration with NLP researchers for decades. However, many recent breakthroughs, such as large transformer based language models, have provided new opportunities for solving interesting, but difficult problems. One such problem is assigning sentiment to reviews of educators{'} performance. We present EduSenti: a corpus of 1,163 Albanian and 624 English reviews of educational instructor{'}s performance reviews annotated for sentiment, emotion and educational topic. In this work, we experiment with fine-tuning several language models on the EduSenti corpus and then compare with an Albanian masked language trained model from the last XLM-RoBERTa checkpoint. We show promising results baseline results, which include an F1 of 71.9 in Albanian and 73.8 in English. Our contributions are: (i) a sentiment analysis corpus in Albanian and English, (ii) a large Albanian corpus of crawled data useful for unsupervised training of language models, and (iii) the source code for our experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nuci-etal-2024-roberta">
<titleInfo>
<title>RoBERTa Low Resource Fine Tuning for Sentiment Analysis in Albanian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krenare</namePart>
<namePart type="given">Pireva</namePart>
<namePart type="family">Nuci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Landes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Di Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The education domain has been a popular area of collaboration with NLP researchers for decades. However, many recent breakthroughs, such as large transformer based language models, have provided new opportunities for solving interesting, but difficult problems. One such problem is assigning sentiment to reviews of educators’ performance. We present EduSenti: a corpus of 1,163 Albanian and 624 English reviews of educational instructor’s performance reviews annotated for sentiment, emotion and educational topic. In this work, we experiment with fine-tuning several language models on the EduSenti corpus and then compare with an Albanian masked language trained model from the last XLM-RoBERTa checkpoint. We show promising results baseline results, which include an F1 of 71.9 in Albanian and 73.8 in English. Our contributions are: (i) a sentiment analysis corpus in Albanian and English, (ii) a large Albanian corpus of crawled data useful for unsupervised training of language models, and (iii) the source code for our experiments.</abstract>
<identifier type="citekey">nuci-etal-2024-roberta</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1233</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14146</start>
<end>14151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoBERTa Low Resource Fine Tuning for Sentiment Analysis in Albanian
%A Nuci, Krenare Pireva
%A Landes, Paul
%A Di Eugenio, Barbara
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nuci-etal-2024-roberta
%X The education domain has been a popular area of collaboration with NLP researchers for decades. However, many recent breakthroughs, such as large transformer based language models, have provided new opportunities for solving interesting, but difficult problems. One such problem is assigning sentiment to reviews of educators’ performance. We present EduSenti: a corpus of 1,163 Albanian and 624 English reviews of educational instructor’s performance reviews annotated for sentiment, emotion and educational topic. In this work, we experiment with fine-tuning several language models on the EduSenti corpus and then compare with an Albanian masked language trained model from the last XLM-RoBERTa checkpoint. We show promising results baseline results, which include an F1 of 71.9 in Albanian and 73.8 in English. Our contributions are: (i) a sentiment analysis corpus in Albanian and English, (ii) a large Albanian corpus of crawled data useful for unsupervised training of language models, and (iii) the source code for our experiments.
%U https://aclanthology.org/2024.lrec-main.1233
%P 14146-14151
Markdown (Informal)
[RoBERTa Low Resource Fine Tuning for Sentiment Analysis in Albanian](https://aclanthology.org/2024.lrec-main.1233) (Nuci et al., LREC-COLING 2024)
ACL