Basic search of sub automata application to electronic dictionaries

This paper we present a new method to detect and compute a set of sub structures of an automaton. This method is applied through a search algorithm for sub automata recognition and used in natural language processing (NLP) applications such as dictionaries. This algorithm is based on the notion of height and cardinality of states; it visits the states of a minimal deterministic finite state automaton in a depth first order where each state is inspected once.