Inferring Descriptive Generalisations of Formal Languages

Abstract

In the present paper, we introduce a variant of Gold-style learners that is not required to infer precise descriptions of the languages in a class, but that must find descriptive patterns, i.e., optimal generalisations within a class of pattern languages. Our first main result characterises those indexed families of recursive languages that can be inferred by such learners, and we demonstrate that this characterisation shows enlightening connections to Angluinʼs corresponding result for exact inference. Furthermore, this result reveals that our model can be interpreted as an instance of a natural extension of Goldʼs model of language identification in the limit. Using a notion of descriptiveness that is restricted to the natural subclass of terminal-free E-pattern languages, we introduce a generic inference strategy, and our second main result characterises those classes of languages that can be generalised by this strategy. This characterisation demonstrates that there are major classes of languages that can be generalised in our model, but not be inferred by a normal Gold-style learner. Our corresponding technical considerations lead to insights of intrinsic interest into combinatorial and algorithmic properties of pattern languages.