ICIX: A Semantic Information Extraction Architecture

Abstract

Public and private organizations produce and store huge amounts of documents which contain information about their domains in non-structured formats. Although from the final user’s point of view we can rely on different retrieval tools to access such data, the progressive structuring of such documents has important benefits for daily operations. While there exist many approaches to extract information in open domains, we lack tools flexible enough to adapt themselves to the particularities of different domains. In this paper, we present the design and implementation of ICIX, an architecture to extract structured information from text documents. ICIX aims at obtaining specific information within a given domain, defined by means of an ontology which guides the extraction process. Besides, to optimize such an extraction, ICIX relies on document classification and data curation adapted to the particular domain. Our proposal has been implemented and evaluated in the specific context of managing legal documents, with promising results.