Performing Named Entity Resolution in Enterprise Scenarios – Experiences, Lessons Learned and Methodological Guidelines
Speaker: Dr. Panos Alexopoulo
Abstract: Named Entity Resolution (NER) is an information extraction task that involves detecting mentions of named entities (e.g. people, organisations or locations) within texts and mapping them to their corresponding entities in a given knowledge source. Systems and frameworks for performing NER have been developed both by the academia and the industry with different features and capabilities. The goal of this presentation is to describe our experiences from implementing NER solutions in a number of real-world application scenarios and share some key lessons we learned with respect to their applicability and effectiveness. Moreover, we shall describe a metric-based methodological framework that allowed us to understand and optimize the performance of our NER solution in each of these scenarios.
Time: 14:00-15:00, 3rd Dec. 2014 Venue: Meston 2