@inproceedings{ullah-etal-2023-comparing,
title = "Comparing Prompt-Based and Standard Fine-Tuning for {U}rdu Text Classification",
author = "Ullah, Faizad and
Azam, Ubaid and
Faheem, Ali and
Kamiran, Faisal and
Karim, Asim",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.449",
doi = "10.18653/v1/2023.findings-emnlp.449",
pages = "6747--6754",
abstract = "Recent advancements in natural language processing have demonstrated the efficacy of pre-trained language models for various downstream tasks through prompt-based fine-tuning. In contrast to standard fine-tuning, which relies solely on labeled examples, prompt-based fine-tuning combines a few labeled examples (few shot) with guidance through prompts tailored for the specific language and task. For low-resource languages, where labeled examples are limited, prompt-based fine-tuning appears to be a promising alternative. In this paper, we compare prompt-based and standard fine-tuning for the popular task of text classification in Urdu and Roman Urdu languages. We conduct experiments using five datasets, covering different domains, and pre-trained multilingual transformers. The results reveal that significant improvement of up to 13{\%} in accuracy is achieved by prompt-based fine-tuning over standard fine-tuning approaches. This suggests the potential of prompt-based fine-tuning as a valuable approach for low-resource languages with limited labeled data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ullah-etal-2023-comparing">
<titleInfo>
<title>Comparing Prompt-Based and Standard Fine-Tuning for Urdu Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faizad</namePart>
<namePart type="family">Ullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ubaid</namePart>
<namePart type="family">Azam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Faheem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="family">Kamiran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asim</namePart>
<namePart type="family">Karim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advancements in natural language processing have demonstrated the efficacy of pre-trained language models for various downstream tasks through prompt-based fine-tuning. In contrast to standard fine-tuning, which relies solely on labeled examples, prompt-based fine-tuning combines a few labeled examples (few shot) with guidance through prompts tailored for the specific language and task. For low-resource languages, where labeled examples are limited, prompt-based fine-tuning appears to be a promising alternative. In this paper, we compare prompt-based and standard fine-tuning for the popular task of text classification in Urdu and Roman Urdu languages. We conduct experiments using five datasets, covering different domains, and pre-trained multilingual transformers. The results reveal that significant improvement of up to 13% in accuracy is achieved by prompt-based fine-tuning over standard fine-tuning approaches. This suggests the potential of prompt-based fine-tuning as a valuable approach for low-resource languages with limited labeled data.</abstract>
<identifier type="citekey">ullah-etal-2023-comparing</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.449</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.449</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6747</start>
<end>6754</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Prompt-Based and Standard Fine-Tuning for Urdu Text Classification
%A Ullah, Faizad
%A Azam, Ubaid
%A Faheem, Ali
%A Kamiran, Faisal
%A Karim, Asim
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ullah-etal-2023-comparing
%X Recent advancements in natural language processing have demonstrated the efficacy of pre-trained language models for various downstream tasks through prompt-based fine-tuning. In contrast to standard fine-tuning, which relies solely on labeled examples, prompt-based fine-tuning combines a few labeled examples (few shot) with guidance through prompts tailored for the specific language and task. For low-resource languages, where labeled examples are limited, prompt-based fine-tuning appears to be a promising alternative. In this paper, we compare prompt-based and standard fine-tuning for the popular task of text classification in Urdu and Roman Urdu languages. We conduct experiments using five datasets, covering different domains, and pre-trained multilingual transformers. The results reveal that significant improvement of up to 13% in accuracy is achieved by prompt-based fine-tuning over standard fine-tuning approaches. This suggests the potential of prompt-based fine-tuning as a valuable approach for low-resource languages with limited labeled data.
%R 10.18653/v1/2023.findings-emnlp.449
%U https://aclanthology.org/2023.findings-emnlp.449
%U https://doi.org/10.18653/v1/2023.findings-emnlp.449
%P 6747-6754
Markdown (Informal)
[Comparing Prompt-Based and Standard Fine-Tuning for Urdu Text Classification](https://aclanthology.org/2023.findings-emnlp.449) (Ullah et al., Findings 2023)
ACL