Extracting Context-Free Grammars from Recurrent Neural Networks using Tree-Automata Learning and A* Search - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Extracting Context-Free Grammars from Recurrent Neural Networks using Tree-Automata Learning and A* Search

Résumé

This paper presents (i) an active learning algorithm for visibly pushdown grammars and (ii) shows its applicability for learning surrogate models of recurrent neural networks (RNNs) trained on context-free languages. Such surrogate models may be used for verification or explainability. Our learning algorithm makes use of the proximity of visibly pushdown languages and regular tree languages and builds on an existing learning algorithm for regular tree languages. Equivalence tests between a given RNN and a hypothesis grammar rely on a mixture of A* search and random sampling. An evaluation of our approach on a set of RNNs from the literature shows good preliminary results.
Fichier principal
Vignette du fichier
icgi-2020_21.pdf (385.96 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03285433 , version 1 (24-08-2021)

Identifiants

  • HAL Id : hal-03285433 , version 1

Citer

Benoît Barbot, Benedikt Bollig, Alain Finkel, Serge Haddad, Igor Khmelnitsky, et al.. Extracting Context-Free Grammars from Recurrent Neural Networks using Tree-Automata Learning and A* Search. ICGI 2021 - 15th International Conference on Grammatical Inference, Aug 2021, New York City / Virtual, United States. pp.113-129. ⟨hal-03285433⟩
176 Consultations
194 Téléchargements

Partager

Gmail Facebook X LinkedIn More