@inproceedings{subedi-etal-2024-exploring-potential,
title = "Exploring the Potential of Large Language Models ({LLM}s) for Low-resource Languages: A Study on Named-Entity Recognition ({NER}) and Part-Of-Speech ({POS}) Tagging for {N}epali Language",
author = "Subedi, Bipesh and
Regmi, Sunil and
Bal, Bal Krishna and
Acharya, Praveen",
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.611",
pages = "6974--6979",
abstract = "Large Language Models (LLMs) have made significant advancements in Natural Language Processing (NLP) by excelling in various NLP tasks. This study specifically focuses on evaluating the performance of LLMs for Named Entity Recognition (NER) and Part-of-Speech (POS) tagging for a low-resource language, Nepali. The aim is to study the effectiveness of these models for languages with limited resources by conducting experiments involving various parameters and fine-tuning and evaluating two datasets namely, ILPRL and EBIQUITY. In this work, we have experimented with eight LLMs for Nepali NER and POS tagging. While some prior works utilized larger datasets than ours, our contribution lies in presenting a comprehensive analysis of multiple LLMs in a unified setting. The findings indicate that NepBERTa, trained solely in the Nepali language, demonstrated the highest performance with F1-scores of 0.76 and 0.90 in ILPRL dataset. Similarly, it achieved 0.79 and 0.97 in EBIQUITY dataset for NER and POS respectively. This study not only highlights the potential of LLMs in performing classification tasks for low-resource languages but also compares their performance with that of alternative approaches deployed for the tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="subedi-etal-2024-exploring-potential">
<titleInfo>
<title>Exploring the Potential of Large Language Models (LLMs) for Low-resource Languages: A Study on Named-Entity Recognition (NER) and Part-Of-Speech (POS) Tagging for Nepali Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bipesh</namePart>
<namePart type="family">Subedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Praveen</namePart>
<namePart type="family">Acharya</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>Large Language Models (LLMs) have made significant advancements in Natural Language Processing (NLP) by excelling in various NLP tasks. This study specifically focuses on evaluating the performance of LLMs for Named Entity Recognition (NER) and Part-of-Speech (POS) tagging for a low-resource language, Nepali. The aim is to study the effectiveness of these models for languages with limited resources by conducting experiments involving various parameters and fine-tuning and evaluating two datasets namely, ILPRL and EBIQUITY. In this work, we have experimented with eight LLMs for Nepali NER and POS tagging. While some prior works utilized larger datasets than ours, our contribution lies in presenting a comprehensive analysis of multiple LLMs in a unified setting. The findings indicate that NepBERTa, trained solely in the Nepali language, demonstrated the highest performance with F1-scores of 0.76 and 0.90 in ILPRL dataset. Similarly, it achieved 0.79 and 0.97 in EBIQUITY dataset for NER and POS respectively. This study not only highlights the potential of LLMs in performing classification tasks for low-resource languages but also compares their performance with that of alternative approaches deployed for the tasks.</abstract>
<identifier type="citekey">subedi-etal-2024-exploring-potential</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.611</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6974</start>
<end>6979</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Potential of Large Language Models (LLMs) for Low-resource Languages: A Study on Named-Entity Recognition (NER) and Part-Of-Speech (POS) Tagging for Nepali Language
%A Subedi, Bipesh
%A Regmi, Sunil
%A Bal, Bal Krishna
%A Acharya, Praveen
%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 subedi-etal-2024-exploring-potential
%X Large Language Models (LLMs) have made significant advancements in Natural Language Processing (NLP) by excelling in various NLP tasks. This study specifically focuses on evaluating the performance of LLMs for Named Entity Recognition (NER) and Part-of-Speech (POS) tagging for a low-resource language, Nepali. The aim is to study the effectiveness of these models for languages with limited resources by conducting experiments involving various parameters and fine-tuning and evaluating two datasets namely, ILPRL and EBIQUITY. In this work, we have experimented with eight LLMs for Nepali NER and POS tagging. While some prior works utilized larger datasets than ours, our contribution lies in presenting a comprehensive analysis of multiple LLMs in a unified setting. The findings indicate that NepBERTa, trained solely in the Nepali language, demonstrated the highest performance with F1-scores of 0.76 and 0.90 in ILPRL dataset. Similarly, it achieved 0.79 and 0.97 in EBIQUITY dataset for NER and POS respectively. This study not only highlights the potential of LLMs in performing classification tasks for low-resource languages but also compares their performance with that of alternative approaches deployed for the tasks.
%U https://aclanthology.org/2024.lrec-main.611
%P 6974-6979
Markdown (Informal)
[Exploring the Potential of Large Language Models (LLMs) for Low-resource Languages: A Study on Named-Entity Recognition (NER) and Part-Of-Speech (POS) Tagging for Nepali Language](https://aclanthology.org/2024.lrec-main.611) (Subedi et al., LREC-COLING 2024)
ACL