Salman Masih

Dr. Salman Masih

Department of Computer Science, Air University, Islamabad, Islāmābād, Pakistan
orcid
Ph.D. in Computer Science | NLP | Large Language Models | M...

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
Salman MasihSalman Masih
Salman Masih
MHMehdi Hassan
Mehdi Hassan
LFLabiba Gillani Fahad
Labiba Gillani Fahad
Bilal HassanBilal Hassan
Bilal Hassan
The emergence of large language models (LLMs) has revolutionized the trajectory of NLP research. Transformers, combined with attention mechanisms, have increased computational power, and massive datasets have led to the emergence of pre-trained large language models (PLLMs), which offer promising possibilities for multilingual applications in low-resource settings. However, the scarcity of annotated resources and suitably pre-trained models continues to pose a significant hurdle for the low-resource abstractive text summarization of legal texts, particularly in Urdu. This study presents a transfer learning approach using pre-trained multilingual large models (the mBART and mT5, Small, Base, and Large) to generate abstractive summaries of Urdu legal texts. A curated dataset was developed with legal experts, who produced ground-truth summaries. The models were fine-tuned on this domain-specific corpus to adapt them for low-resource legal summarization. The experimental results demonstrated that the mT5-Large, fine-tuned on Urdu legal texts, outperforms all other evaluated models across standard summarization metrics, achieving ROUGE-1 scores of 0.7889, ROUGE-2 scores of 0.5961, and ROUGE-L scores of 0.7813. This indicates its strong capacity to generate fluent, coherent, and legally accurate summaries. The mT5-Base model closely follows with ROUGE-1 = 0.7774, while the mT5-Small shows moderate performance (ROUGE-1 = 0.6406), with reduced fidelity in capturing legal structure. The mBART50 model, despite being fine-tuned on the same legal corpus, performs lower (ROUGE-1 = 0.5914), revealing its relative limitations in this domain. Notably, models trained or fine-tuned on non-legal, out-of-domain data, such as the urT5 (ROUGE-1 = 0.3912), the mT5-XLSUM (ROUGE-1 = 0.0582), and the mBART50 (XLSUM) (ROUGE-1 = 0.0545), exhibit poor generalization to legal summaries, underscoring the necessity of domain adaptation when working in low-resource legal contexts. These findings highlight the effectiveness of fine-tuning multilingual LLMs for domain-specific tasks. The gains in legal summarization demonstrate the practical value of transfer learning in low-resource settings and the broader potential of AI-driven tools for legal document processing, information retrieval, and decision support.

1 January 2019 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
Salman MasihSalman Masih
Salman Masih
IIImran Ihsan
Imran Ihsan
Motion Picture Production has always been a risky and pricey venture. Bollywood alone has released approximately 120 movies in 2017. It is disappointing that only 8% of the movies have made to box office and the remaining 92% failed to return the total cost of production. Studies have explored several determinants that make a motion picture success at box office for Hollywood movies including academy awards. However, same can’t be said for Bollywood movies as there is significantly less research has been conducted to predict their success of a movie. Research also shows no evidence of using academy awards to predict a Bollywood movie’s success. This paper investigates the possibility; does an academy award such as ZeeCine or IIFA, previously won by the actor, playing an important role in movie, impact its success or not? In order to measure, the importance of these academy awards towards a movie’s success, a possible revenue for the movie is predicted using the academy awards information and categorizing the movie in different revenue range classes. We have collected data from multiple sources like Wikipedia, IMDB and BoxOfficeIndia. Various machine-learning algorithms such as Decision Tree, Random Forest, Artificial Neural Networks, Naïve Bayes and Bayesian Networks are used for the said purpose. Experiment and their results show that academy awards slightly increase the accuracy making an academy award a non-dominating ingredient of predicating movie’s success on box office.