Ammar Ahmed Taha Mohammed
Identity verified by the researcher via institutional email.
Role not yet determined
Research Areas
Biography and Research Information
OverviewAI-generated summary
Ammar Ahmed Taha Mohammed's research focuses on developing and evaluating computational pipelines for entity resolution. His work involves integrating advanced techniques such as Large Language Models (LLMs), semantic clustering, and household movement analysis to improve the accuracy and efficiency of identifying and linking distinct records that refer to the same real-world entity. He has developed synthetic data generation tools, including the "Synthetic Occupancy Generator 2.0," to create reproducible benchmarks for testing and validating these entity resolution methodologies. These artifacts are designed to facilitate scenario-driven evaluations, ensuring that the performance of different approaches can be rigorously assessed under various conditions.
Metrics
- Publications: 4
Selected Publications
-
A Hybrid Entity Resolution Pipeline Integrating LLM Intelligence, Semantic Clustering, and Household Movement Analysis (2026)
-
MaTaha-ualr/Synthetic Occupancy Generator 2.0: Final Reproducibility Artifact for Scenario-Driven Entity Resolution Benchmarks (2026)
-
MaTaha-ualr/Synthetic-Occupancy-Generator-data_pipeline: SOG Paper Reproducibility Artifact — 2026.07.24 (2026)
-
MaTaha-ualr/Synthetic Occupancy Generator 2.0: Final Reproducibility Artifact for Scenario-Driven Entity Resolution Benchmarks (2026)
Collaboration Network
Top Collaborators
- A Hybrid Entity Resolution Pipeline Integrating LLM Intelligence, Semantic Clustering, and Household Movement Analysis
- A Hybrid Entity Resolution Pipeline Integrating LLM Intelligence, Semantic Clustering, and Household Movement Analysis
Similar Researchers
Based on overlapping research topics