Publications/Natural Language Processing & LLMs for Low-Resource Languages
Conference · 2009
N-Gram Based Authorship Attribution in Urdu Poetry
Agha Ali Raza, Awais Athar, Sajid Nadeem
Conference on Language and Technology (CLT) 2009, Lahore, Pakistan
Summary
Can a computer tell which poet wrote a verse? Authorship attribution systems learn a writer's vocabulary and style and then judge new text statistically. We built a system that applies one existing and one modified attribution technique to Urdu poetry, using word-level n-gram language models, and report the results along with the practical issues involved in training such models for Urdu.
Cite this paper
Agha Ali Raza, Awais Athar, Sajid Nadeem. N-Gram Based Authorship Attribution in Urdu Poetry. Conference on Language and Technology (CLT) 2009, Lahore, Pakistan.
@inproceedings{raza2009n,
author = {Agha Ali Raza and Awais Athar and Sajid Nadeem},
title = {{N-Gram Based Authorship Attribution in Urdu Poetry}},
booktitle = {Conference on Language and Technology (CLT) 2009, Lahore, Pakistan},
year = {2009},
url = {https://aghaaliraza.com/publications/2009--CLT--N-Gram_Based_Authorship_Attribution_in_Urdu_Poetry.pdf}
}
- IRTIQA: Evolving in English, Evaluated in Urdu — Does Agent Self-Evolution Transfer Across Languages?Findings of EACL 2027, Athens, Greece
- UrduCultureQA: A Culturally Grounded Benchmark for Urdu Question Answering and Alignment EvaluationFindings of EACL 2027, Athens, Greece
- Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu BenchmarkEMNLP 2026 (Main), Budapest, Hungary
- Evaluating Robustness of LLM-Based Ambient Scribes for SOAP Note GenerationCHIL 2026 (Conference on Health, Inference, and Learning), PMLR vol. 333
- Kahaani: A Multimodal Co-Creative Storytelling SystemEACL 2026 Student Research Workshop, Rabat, Morocco