Learning Recursive Automata from Positive Examples

Isabelle Tellier (1, 2)

1 LIFL - Laboratoire d'Informatique Fondamentale de Lille
2 MOSTRARE - Modeling Tree Structures, Machine Learning, and Information Extraction

In this theoretical paper, we compare the "classical" learning techniques used to infer regular grammars from positive examples with the ones used to infer categorial grammars. To this aim, we first study how to translate finite state automata into categorial grammars and back. We then show that the generalization operators employed in both domains can be compared, and that their result can always be represented by generalized automata, called "recursive automata". The relation between these generalized automata and categorial grammars is studied in detail. Finally, new learnable subclasses of categorial grammars are defined, for which learning from strings is nearly not more expensive than from structures.

Domains: Machine Learning [cs.LG]; Artificial Intelligence [cs.AI]; Formal Languages and Automata Theory [cs.FL]

Isabelle Tellier. Learning Recursive Automata from Positive Examples. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2006, New Methods in Machine Learning. Theory and Applications, 20 (6), pp.775-804. ⟨10.3166/ria.20.775-804⟩. ⟨inria-00470101⟩