Information Extraction from Text Based on Semantic Inferentialism

One of the growing needs of information extraction (IE) from text is that the IE system must be able to perform enriched inferences in order to discover and extract information. We argue that one reason for the current limitation of the approaches that use semantics for that is that they are based on ontologies that express the characteristics of things represented by names, and seek to draw inferences and to extract information based on such characteristics, disregarding the linguistic praxis (i.e. the uses of the natural language). In this paper, we describe a generic architecture for IE systems based on Semantic Inferentialism. We propose a model that seeks to express the inferential power of concepts and how these concepts, combined in sentence structures, contribute to the inferential power of sentences. We demonstrate the validity of the approach and evaluate it by deploying an application for extracting information about crime reported in on line newspapers.