Scholar
Asim Karim
Google Scholar ID: NXFekJ4AAAAJ
Professor, Lahore University of Management Sciences (LUMS)
Citations & Impact
Citations
1,845
H-index
21
i10-index
36
Publications
20
Co-authors
33
list available
Contact
Publications
Resume
Academic Achievements
- Published multiple papers in various journals and conferences such as Language Resources and Evaluation, Scientific Reports, IEEE Access, etc. Specific publications include:
- - Part of Speech (POS) Tagging in Roman Urdu: Datasets and Models
- - Prompt-Based Fine-Tuning with Multilingual Transformers for Language-Independent Sentiment Analysis
- - Data-Driven Uplift Modeling
- - Comparing Prompt-Based and Standard Fine-Tuning for Urdu Text Classification
- - Roman Urdu Toxic Comment Classification
- - Hate-speech and Offensive Language Detection in Roman Urdu
- - A Multi-cascaded Model with Data Augmentation for Enhanced Paraphrase Detection in Short Text
- - A Clustering Framework for Normalizing Roman Urdu
- - A Multi-cascaded Deep Model for Bilingual SMS Classification
- - Balancing Prediction Errors for Robust Sentiment Classification
- - ALAP: Accessible LaTeX-based Mathematical Document Authoring and Presentation
- - Exploiting Reject Option in Classification for Social Discrimination Control
- - NELasso: Group-Sparse Modeling for Characterizing Relations Among Named Entities in News Articles
- - CDIM: Document Clustering by Discrimination Information Maximization
- - Controlling Attribute Effect in Linear Regression Models
Research Experience
- Directs the Knowledge and Data Engineering (KADE) Lab at LUMS.
Education
- Ph.D. from The Ohio State University; M.S. from The Ohio State University; B.Sc. from UET Lahore
Background
- Research interests include data mining and machine learning algorithms and applications. Current research directions include natural language processing of Urdu and other low-resource languages, text categorization and clustering, and causal analysis and inference from observed data. He also works on assistive technologies for persons with disabilities, particularly focusing on technologies for visually impaired individuals.
