Work

R-R at AbjadAuthorID Shared Task: A Fine-Tuned Approach for Kurdish Authorship Identification

Year: 2026

Type: conference-paper

Abstract: Authorship identification is a fundamental task in natural language processing and computational stylistics.Despite significant advancements in high-resource languages, lowresource languagesparticularly those utilizing non-Latin scriptsremain largely underexplored, leaving a critical gap in resources and benchmarks for this linguistically distinct, lowresource language.Addressing this oversight, this paper presents Task 3 of AbjadNLP 2026, the first shared task dedicated to authorship identification for Kurdish.The task introduces a newly constructed dataset designed to capture the unique phonological and orthographic features of Sorani Kurdish and formulate the task as a closed-set multiclass classification problem.To establish a robust baseline, we fine-tune the pretrained XLM-RoBERTa model to capture authorial, stylistic patterns.Experimental results on the test set demonstrate the efficacy of transformer-based representations for this domain, achieving an accuracy of approximately 75%.

Source: Workshop on NLP for Languages Using Arabic Script (AbjadNLP)

DOI: 10.18653/v1/2026.abjadnlp-1.67

Authors: Rania Azad M. San Ahmed, Rebwar M. Nabi

Institutions: Sulaimani Polytechnic University, Kurdistan Technical Institute

Language: English

Topic: Authorship Attribution and Profiling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7140076280

FWCI:

Cites: 1

Cited by:

Related to: 10