Text Mining and Image Anomaly Explanation with Machine Consciousness

Abstract

In the present paper a series of implemented computer systems of information extraction for question answering that generate explanations of this extraction from text and image are presented. These computer generated explanations of the performance of a computer system may function as a criterion of the exhibition of Machine Consciousness. Additionally the systems presented in the present paper may facilitate their communication with their users. Such communication is very useful for building the confidence of a user to a computer system. The main information extraction method used by the systems described here is the one based on a finite state automaton. Following the presentation of systems that have been implemented by our group for various text bases a novel development is reported concerning the explanation of image anomalies. The presentation of our novel work is helped by an example of anomaly detection and explanation in modern paintings.