A knowledge-based approach to entity identification and classification in natural language text

International audienceWe present a system for entity identification in free text. Each entity extracted will be identified as an entity from the system’s knowledge base – an ontology. We propose an algorithm that detects in a single pass the most probable related entity assignations instead of individually checking every possible entity combination. This unsupervised system employs graph algorithms applied on a graph extracted from the ontology as well as implementing a entity path scoring function to provide the most probable related entity assignations. We present the system’s implementation and results, as well as its strong and weak-points