Passive Learning of Lattice Automata from Recurrent Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Slimi, Jaouhar, Gall, Tristan Le, Lemesle, Augustin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914320067067904
author Slimi, Jaouhar
Gall, Tristan Le
Lemesle, Augustin
author_facet Slimi, Jaouhar
Gall, Tristan Le
Lemesle, Augustin
contents We present a passive automata learning algorithm that can extract automata from recurrent networks with very large or even infinite alphabets. Our method combines overapproximations from the field of Abstract Interpretation and passive automata learning from the field of Grammatical Inference. We evaluate our algorithm by first comparing it with the state-of-the-art automata extraction algorithm from Recurrent Neural Networks trained on Tomita grammars. Then, we extend these experiments to regular languages with infinite alphabets, which we propose as a novel benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22489
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Passive Learning of Lattice Automata from Recurrent Neural Networks
Slimi, Jaouhar
Gall, Tristan Le
Lemesle, Augustin
Formal Languages and Automata Theory
We present a passive automata learning algorithm that can extract automata from recurrent networks with very large or even infinite alphabets. Our method combines overapproximations from the field of Abstract Interpretation and passive automata learning from the field of Grammatical Inference. We evaluate our algorithm by first comparing it with the state-of-the-art automata extraction algorithm from Recurrent Neural Networks trained on Tomita grammars. Then, we extend these experiments to regular languages with infinite alphabets, which we propose as a novel benchmark.
title Passive Learning of Lattice Automata from Recurrent Neural Networks
topic Formal Languages and Automata Theory
url https://arxiv.org/abs/2509.22489