A generic information extraction architecture for financial applications

The advent of computing has exacerbated the problem of overwhelming informa tion. To manage the deluge of information, information extraction systems c an he used to automatically extract relevant information from free-form tex t for update to databases or for report generation. One of the major challe nges to the information extraction is the representation of domain knowledg e in the task, that is how to represent the meaning of the input text, the knowledge of the field of application, and the knowledge about the target i nformation to be extracted. We have chosen a directed graph structure, a do main ontology and a frame representation, respectively. We have further dev eloped a generic information extraction (GIE) architecture that combines th ese knowledge structures for the task of processing. The GIE system is able to extract information from free-form text, further infer and derive new i nformation. It analyzes the input text into a graph structure and subsequen tly unifies the graph and the ontology for extraction of relevant informati on, driven by the frame structure during a template filling process. The GI E system has been adopted for use in the message formatting expert system, a large-scale information extraction system for a specific financial applic ation within a major bank in Singapore. (C) 1999 Elsevier Science Ltd. All rights reserved.