BI-style relation discovery among entities in text

Business Intelligence (BI) over unstructured text is under intense scrutiny both in industry and research. Recent work in this field includes automatic integration of unstructured text into BI systems, model recognition, and probabilistic databases to handle uncertainty of Information Extraction (IE) results. Our aim is to use analytics to discover statistically relevant and unknown relationship between entities in documents' fragments. We present a method for transforming IE results to an OLAP model and we demonstrate it in a real world scenario for the SAP Community Network.