A Logic-Based Tool for Semantic Information Extraction

Abstract

Recognizing and extracting meaningful information from unstructured Web documents, taking into account their semantics, is an important problem in information and knowledge management. This paper describes H$\imath$LεX, a system implementing a novel logic-based approach to information extraction from unstructured documents. The approach adopted in the H$\imath$LεX system is founded on a new two-dimensional representation of documents, and heavily exploits DLP ⁺ – an extension of disjunctive logic programming for ontology representation and reasoning, which has been recently implemented on top of the DLV system. Unlike previous systems, which are mainly syntactic, H$\imath$LεX combines both semantic and syntactic knowledge for a powerful information extraction. Ontologies, representing the semantics of the domain of the information to be extracted, are encoded in DLP ⁺, while the extraction patterns are encoded by regular expressions in an ad hoc two-dimensional grammar. These regular expressions are (internally) translated into DLP ⁺ rules, whose execution yields the actual extraction of information from the input document. H$\imath$LεX allows the semantic information extraction from both HTML pages and flat text documents. The usefulness of Hilex has been already confirmed also in practice, as the system has been successfully employed in two advanced applications in the e-health and e-finance domains.