A Congruence-based Approach to Active Automata Learning from Neural Language Models

Franz Mayr, Sergio Yovine, Matías Carrasco, Federico Pan, Federico Vilensky

Abstract: The paper proposes an approach for probably approximately correct active learning of probabilistic automata (PDFA) from neural language models. It is based on a congruence over strings which is parameterized by an equivalence relation over probability distributions. The learning algorithm is implemented using a tree data structure of arbitrary (possibly unbounded) degree. The implementation is evaluated with several equivalences on LSTM and Transformer-based neural language models from different application domains.