@inproceedings{wazir-etal-2026-upr,
title = "{UPR} at {S}em{E}val-2026 Task 9: Polarization Detection in {U}rdu with Language-Specific Transformer and Data Augmentation",
author = "Wazir, Alishba and
Asad Khan, Muhammad and
Rashid, Junaid and
Hayat, Shamaila and
Kanwal, Samira",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.332/",
pages = "2635--2641",
ISBN = "979-8-89176-414-9",
abstract = "This paper addresses polarization detection in Urdu, a low-resource language characterized by complex morphology and insufficient annotated data. We formulate the task as a binary classification problem of social media posts into polarized and non-polarized categories. Our approach is based on Urdu-BERT, a language-specific transformer model combined with language-specific preprocessing, duplicate removal, and data augmentation to mitigate class imbalance and improve generalization. Experimental results show that the fine-tuned Urdu-BERT outperforms TF-IDF-based lexical machine learning baselines and achieves strong performance relative to multilingual transformer baselines. The findings indicate that language-specific pretrained transformers, when combined with appropriate preprocessing and augmentation strategies, provide an effective and generalizable framework for low-resource Urdu polarization detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wazir-etal-2026-upr">
<titleInfo>
<title>UPR at SemEval-2026 Task 9: Polarization Detection in Urdu with Language-Specific Transformer and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alishba</namePart>
<namePart type="family">Wazir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Asad Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junaid</namePart>
<namePart type="family">Rashid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shamaila</namePart>
<namePart type="family">Hayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Kanwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper addresses polarization detection in Urdu, a low-resource language characterized by complex morphology and insufficient annotated data. We formulate the task as a binary classification problem of social media posts into polarized and non-polarized categories. Our approach is based on Urdu-BERT, a language-specific transformer model combined with language-specific preprocessing, duplicate removal, and data augmentation to mitigate class imbalance and improve generalization. Experimental results show that the fine-tuned Urdu-BERT outperforms TF-IDF-based lexical machine learning baselines and achieves strong performance relative to multilingual transformer baselines. The findings indicate that language-specific pretrained transformers, when combined with appropriate preprocessing and augmentation strategies, provide an effective and generalizable framework for low-resource Urdu polarization detection.</abstract>
<identifier type="citekey">wazir-etal-2026-upr</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.332/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2635</start>
<end>2641</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UPR at SemEval-2026 Task 9: Polarization Detection in Urdu with Language-Specific Transformer and Data Augmentation
%A Wazir, Alishba
%A Asad Khan, Muhammad
%A Rashid, Junaid
%A Hayat, Shamaila
%A Kanwal, Samira
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F wazir-etal-2026-upr
%X This paper addresses polarization detection in Urdu, a low-resource language characterized by complex morphology and insufficient annotated data. We formulate the task as a binary classification problem of social media posts into polarized and non-polarized categories. Our approach is based on Urdu-BERT, a language-specific transformer model combined with language-specific preprocessing, duplicate removal, and data augmentation to mitigate class imbalance and improve generalization. Experimental results show that the fine-tuned Urdu-BERT outperforms TF-IDF-based lexical machine learning baselines and achieves strong performance relative to multilingual transformer baselines. The findings indicate that language-specific pretrained transformers, when combined with appropriate preprocessing and augmentation strategies, provide an effective and generalizable framework for low-resource Urdu polarization detection.
%U https://aclanthology.org/2026.semeval-1.332/
%P 2635-2641
Markdown (Informal)
[UPR at SemEval-2026 Task 9: Polarization Detection in Urdu with Language-Specific Transformer and Data Augmentation](https://aclanthology.org/2026.semeval-1.332/) (Wazir et al., SemEval 2026)
ACL