Semantically Enhanced Passage Retrieval for Business Analysis Activity

Abstract

Business analysis activity often involves the identification and extraction of information from business reports. The unstructured content of business reports poses a challenge to current Business Intelligence technologies. In this paper, we present an application that provides passage retrieval capability, which has been developed for use in business analysis activity at Hewlett-Packard¿ (HP). Preliminary evaluation of the application indicates that the inclusion of domain knowledge such as domain semantics and business intelligence rules plays an important part in system performance. It dramatically reduces the time that analysts spend extracting relevant informative passages within a report or business intelligence. In addition, it can find further relevant information that would have been overlooked by the analyst.