Concurrent Entity Recognition and Relationship Extraction from Unstructured Text

Abstract

Entity recognition and entity relationship extraction are two very important tasks in information extraction. This paper proposes a new method for performing entity recognition and entity relationship extraction concurrently from unstructured text based on Conditional Random Fields (CRFs). This method makes use of entity features, entity relationship features and features of triples which is composed of entities and their relationship to conduct the model training. Preliminary experiment results show that this method can recognize entity and extract entity relationship effectively.