Learning Top-Down Tree Transducers with Regular Domain Inspection

Adrien Boiret (1) , Aurélien Lemay (1) , Joachim Niehren (1)

1 LINKS - Linking Dynamic Data

We study the problem of how to learn tree transformations on a given regular tree domain from a finite sample of input-output examples. We assume that the target tree transformation can be defined by a deterministic top-down tree transducer with regular domain inspection (DTOPi:reg). An RPNI style learning algorithm that solves this problem in polynomial time and with polynomially many examples was presented at Pods'2010, but restricted to the case of path-closed regular domains. In this paper, we show that this restriction can be removed. For this, we present a new normal form for DTOPi:reg by extending the Myhill-Nerode theorem for DTOP to regular domain inspections in a nontrivial manner. The RPNI style learning algorithm can also be lifted but becomes more involved too.

Mots clés: Tree Transducers; Myhill-Nerode Theorem; Normal Form; Gold model Learning

Domaines: Informatique [cs]; Théorie et langage formel [cs.FL]; Apprentissage [cs.LG]

Adrien Boiret, Aurélien Lemay, Joachim Niehren. Learning Top-Down Tree Transducers with Regular Domain Inspection. International Conference on Grammatical Inference 2016, Oct 2016, Delft, Netherlands. ⟨hal-01357186⟩