@inproceedings{ullah-etal-2026-maskedverbalizer,
title = "{M}asked{V}erbalizer: Automatic Verbalizer Construction for Few-Shot Text Classification in Low-Resource Right-to-Left Languages",
author = "Ullah, Faizad and
Sikandar, Furqan and
Waqar, Areeba and
Ali, Faizan and
Ayub, Muhammad Sohaib and
Mushtaq, Mubashar and
Karim, Asim",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.59/",
doi = "10.63317/2ijipj4r77bn",
pages = "795--804",
abstract = "Text classification in low-resource right-to-left languages faces significant challenges due to the scarcity of annotated data and the morphological richness of languages such as Arabic, Urdu, Sindhi, and Pashto. Arabic and Urdu alone are spoken by over 380+ million and 246+ million people worldwide, respectively. Pashto is the national language of Afghanistan, highlighting the importance of effective language technologies. While multilingual Pre-trained Language Models (PLMs) have shown promising results, they typically require extensive labeled datasets and computationally expensive fine-tuning to achieve better performance. Such limitations make these PLMs impractical for the low-resource settings described above. Therefore, we employ a few-shot strategy (zero, 4, or 8 shots) to achieve results comparable to those of standard fine-tuning. In this work, we propose MaskedVerbalizer, a novel technique designed for few-shot text classification. Our method introduces an automatic verbalizer construction approach that generates class-specific label words in 4-shot settings, eliminating the need for extensive manual intervention. Despite maintaining a simple model architecture, MaskedVerbalizer achieves effective performance in classification benchmarks. Experimental results demonstrate that our method effectively addresses the core challenges of low-resource text classification, providing a practical, computationally efficient solution. We achieved accuracies of 90.43{\%} and 92.72{\%} with mBERT and XLM-RoBERTa, respectively, representing improvements of 25{--}30{\%} over soft and automatic verbalizers. The code for MaskedVerbalizer is publicly available at \url{https://github.com/Furqann-hue/MV}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ullah-etal-2026-maskedverbalizer">
<titleInfo>
<title>MaskedVerbalizer: Automatic Verbalizer Construction for Few-Shot Text Classification in Low-Resource Right-to-Left Languages</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">Furqan</namePart>
<namePart type="family">Sikandar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areeba</namePart>
<namePart type="family">Waqar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faizan</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Sohaib</namePart>
<namePart type="family">Ayub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mubashar</namePart>
<namePart type="family">Mushtaq</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>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text classification in low-resource right-to-left languages faces significant challenges due to the scarcity of annotated data and the morphological richness of languages such as Arabic, Urdu, Sindhi, and Pashto. Arabic and Urdu alone are spoken by over 380+ million and 246+ million people worldwide, respectively. Pashto is the national language of Afghanistan, highlighting the importance of effective language technologies. While multilingual Pre-trained Language Models (PLMs) have shown promising results, they typically require extensive labeled datasets and computationally expensive fine-tuning to achieve better performance. Such limitations make these PLMs impractical for the low-resource settings described above. Therefore, we employ a few-shot strategy (zero, 4, or 8 shots) to achieve results comparable to those of standard fine-tuning. In this work, we propose MaskedVerbalizer, a novel technique designed for few-shot text classification. Our method introduces an automatic verbalizer construction approach that generates class-specific label words in 4-shot settings, eliminating the need for extensive manual intervention. Despite maintaining a simple model architecture, MaskedVerbalizer achieves effective performance in classification benchmarks. Experimental results demonstrate that our method effectively addresses the core challenges of low-resource text classification, providing a practical, computationally efficient solution. We achieved accuracies of 90.43% and 92.72% with mBERT and XLM-RoBERTa, respectively, representing improvements of 25–30% over soft and automatic verbalizers. The code for MaskedVerbalizer is publicly available at https://github.com/Furqann-hue/MV.</abstract>
<identifier type="citekey">ullah-etal-2026-maskedverbalizer</identifier>
<identifier type="doi">10.63317/2ijipj4r77bn</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.59/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>795</start>
<end>804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MaskedVerbalizer: Automatic Verbalizer Construction for Few-Shot Text Classification in Low-Resource Right-to-Left Languages
%A Ullah, Faizad
%A Sikandar, Furqan
%A Waqar, Areeba
%A Ali, Faizan
%A Ayub, Muhammad Sohaib
%A Mushtaq, Mubashar
%A Karim, Asim
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F ullah-etal-2026-maskedverbalizer
%X Text classification in low-resource right-to-left languages faces significant challenges due to the scarcity of annotated data and the morphological richness of languages such as Arabic, Urdu, Sindhi, and Pashto. Arabic and Urdu alone are spoken by over 380+ million and 246+ million people worldwide, respectively. Pashto is the national language of Afghanistan, highlighting the importance of effective language technologies. While multilingual Pre-trained Language Models (PLMs) have shown promising results, they typically require extensive labeled datasets and computationally expensive fine-tuning to achieve better performance. Such limitations make these PLMs impractical for the low-resource settings described above. Therefore, we employ a few-shot strategy (zero, 4, or 8 shots) to achieve results comparable to those of standard fine-tuning. In this work, we propose MaskedVerbalizer, a novel technique designed for few-shot text classification. Our method introduces an automatic verbalizer construction approach that generates class-specific label words in 4-shot settings, eliminating the need for extensive manual intervention. Despite maintaining a simple model architecture, MaskedVerbalizer achieves effective performance in classification benchmarks. Experimental results demonstrate that our method effectively addresses the core challenges of low-resource text classification, providing a practical, computationally efficient solution. We achieved accuracies of 90.43% and 92.72% with mBERT and XLM-RoBERTa, respectively, representing improvements of 25–30% over soft and automatic verbalizers. The code for MaskedVerbalizer is publicly available at https://github.com/Furqann-hue/MV.
%R 10.63317/2ijipj4r77bn
%U https://aclanthology.org/2026.lrec-1.59/
%U https://doi.org/10.63317/2ijipj4r77bn
%P 795-804
Markdown (Informal)
[MaskedVerbalizer: Automatic Verbalizer Construction for Few-Shot Text Classification in Low-Resource Right-to-Left Languages](https://aclanthology.org/2026.lrec-1.59/) (Ullah et al., LREC 2026)
ACL