Computer Science doctoral research at Luleå University of Technology, Sweden.
Nudrat Habib · PhD Researcher in Computer Science
Machine learning, NLP and document analysis researcher in Luleå.
Nudrat Habib is a PhD researcher at Luleå University of Technology, Sweden. Her work focuses on machine learning, natural language processing, document analysis, authorship analysis, large language models and data analytics.
Luleå University of TechnologyComputer ScienceMachine LearningDocument Intelligence
Selected publications across machine learning, NLP, LLMs and document analysis.
Years of university teaching, student supervision, labs and mentoring.
Conference and seminar participation listed for SLTC, ICDAR and SSBA/SSDL.
About
Computer Science researcher with teaching, supervision and applied AI experience.
Nudrat has a strong academic background in Computer Science, with experience in research, undergraduate teaching, student supervision, lab design and collaborative academic projects. She previously worked at COMSATS University Islamabad as a Lecturer, Visiting Faculty member and Research Assistant before beginning her PhD in Sweden.
PythonMATLABSQLMachine LearningNLPData Analytics
Research Focus
AI research across language, documents, authorship and data-driven analysis.
Natural Language Processing
Research interests include language technology, authorship analysis, semantic similarity, Urdu language processing and large language model evaluation.
Core focusDocument Analysis
Work includes document visual question answering, OCR, script identification and AI systems for understanding document-based information.
ActiveMachine Learning & Data Analytics
Applied machine learning, deep learning, data mining and explainable analysis for interdisciplinary research problems.
Applied AIPublications
Selected publications and academic papers.
Selected work
LLMs, document intelligence, Urdu NLP and explainable machine learning.
Selected publications include work on false attribution in large language models, instruction-based document analysis, crumb rubber concrete optimization using machine learning and SHAP, Urdu dependency parsing and authorship-analysis trends.
LLM limitationsDocument analysisUrdu NLPSHAP
Projects
Research projects in authorship, documents, language and OCR.
LLMs for Author Attribution
Research on how large language models perform in author-attribution tasks, including reliability gaps and false-attribution risks.
Document Visual Question Answering
Instruction tuning and document understanding research for visual-language systems that answer questions about document images.
Urdu Dependency Parsing & OCR
Low-resource NLP and document analysis work covering Urdu treebank development, dependency parsing and multi-script OCR identification.
Contact
Contact Nudrat for research collaboration.
Email: [email protected] · Alternative: [email protected] · Location: Luleå, Sweden