Comparison of two recent algorithms for grammatical inference of regular languages by means of non-deterministic automata

Abstract

The development of new algorithms that turn out to be convergent and efficient, is a required step for a fruitful use of grammatical inference in the solution of real-world and greater-size problems. In this work, we present two algorithms known as DeLeTe2 and MRIA, which do grammatical inference by means of non-deterministic automata, in contrast to the algorithms more commonly used, which make use of deterministic automata. We consider the advantages and disadvantages of such a change of representation model by means of a detailed description and comparison of the two inference algorithms with regard to the approach used for their implementation, their computational complexity, their termination criteria, and their performance on a corpus of synthetic data.