Computing and Informatics

Entity search is becoming a popular alternative for full text search. Recently Google released its entity search based on confirmed, human-generated data such as Wikipedia. In spite of these developments, the task of entity discovery, search, or relation search in unstructured text remains a major challenge in the fields of information retrieval and information extraction. This paper tries to address that challenge, focusing specifically on entity relation discovery. This is achieved by processing unstructured text using simple information extraction methods, building lightweight semantic graphs and reusing them for entity relation discovery by applying algorithms from graph theory. An important part is also user interaction with semantic graphs, which can significantly improve information extraction results and entity relation search. Entity relations can be discovered by various text mining methods, but the advantage of the presented method lies in the similarity between the lightweight semantics extracted from a text and the information networks available as structured data. Both graph structures have similar properties and similar relation discovery algorithms can be applied. In addition, we can benefit from the integration of such graph data. We provide both a relevance and performance evaluations of the approach and showcase it in several use case applications.