EDU-NER-2025: Named Entity Recognition in Urdu Educational Texts using XLM-RoBERTa with X (formerly Twitter)

2025-04-25

AI Summary

This work addresses the lack of domain-specific annotated data and the difficulty in identifying education-related entities—such as academic roles, course names, and institutional terms—in Urdu educational texts, introducing for the first time the Urdu educational-domain named entity recognition (NER) task. We construct EDU-NER-2025, the first manually annotated, domain-specific NER dataset for Urdu education, comprising 13 fine-grained entity types. To tackle morphological complexity and semantic ambiguity, we perform domain-adaptive fine-tuning of XLM-RoBERTa and augment training data with real-world educational tweets. Our model achieves an F1 score of 86.3% on the EDU-NER-2025 test set, significantly outperforming baseline models. To foster community advancement, we publicly release the dataset, annotation guidelines, and implementation code—thereby filling a critical gap in Urdu educational NLP resources.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Humanities & Computational Social Science
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Named Entity Recognition (NER) plays a pivotal role in various Natural Language Processing (NLP) tasks by identifying and classifying named entities (NEs) from unstructured data into predefined categories such as person, organization, location, date, and time. While extensive research exists for high-resource languages and general domains, NER in Urdu particularly within domain-specific contexts like education remains significantly underexplored. This is Due to lack of annotated datasets for educational content which limits the ability of existing models to accurately identify entities such as academic roles, course names, and institutional terms, underscoring the urgent need for targeted resources in this domain. To the best of our knowledge, no dataset exists in the domain of the Urdu language for this purpose. To achieve this objective this study makes three key contributions. Firstly, we created a manually annotated dataset in the education domain, named EDU-NER-2025, which contains 13 unique most important entities related to education domain. Second, we describe our annotation process and guidelines in detail and discuss the challenges of labelling EDU-NER-2025 dataset. Third, we addressed and analyzed key linguistic challenges, such as morphological complexity and ambiguity, which are prevalent in formal Urdu texts.

Problem

• Lack of Urdu NER datasets for educational texts
• Difficulty in recognizing domain-specific entities in Urdu
• Challenges in Urdu text annotation due to linguistic complexity

Innovation

• Used XLM-RoBERTa for Urdu NER
• Created EDU-NER-2025 annotated dataset
• Addressed Urdu morphological complexity challenges