Inferring pure context-free languages from positive data

Abstract

We study the possibilities to infer pure context-free languages from positive data. We can show that while the whole class of pure context-free languages is not inferable from positive data, it has interesting subclasses which have the desired inference property. We study uniform pure languages, i.e., languages generated by pure grammars obeying restrictions on the length of the right hand sides of their productions, and pure languages generated by deterministic pure grammars.