Intelligent System for Entities Extractions (ISEE) from Natural Language Texts

This paper describes a semantic linguistic processor which extracts the entities and their links from natural language texts. The conceptual model underlying the algorithmic developments is the extended semantic networks (ESN). This paper analyzes the use of the processor for text formalization in various subject fields: economy monitoring, criminal actions, mass media, terrorist activities (in Russian and English). Peculiarities of the texts are taken into account by linguistic knowledge of the processor: the system can be tuned to various subject areas. We describe the use of this processor for text formalization in different subject areas, such as economic crisis monitoring, criminology (summary of incidents, accusatory conclusions, etc.), the mass media documents about terrorist activities, personnel management (autobiographies, resume). Special features of each problem area are examined: the collections of extracted entities, the means for their identification, their connections, occurring contractions, punctuation and special signs, specific character of language constructions, etc. all these special features were taken into account in the linguistic knowledge development.