From Unification Compactness to Learnability

Authors:
Jacek Marciniec
Affiliations:
Faculty of Mathematics and Computer Science, Adam Mickiewicz University, Poznań, Poland. E-mail: jacmar@amu.edu.pl
Venue:
Fundamenta Informaticae
Year:
2007

Citing 3
Cited 0

Identification of unions of languages drawn from an identifiable class

COLT '89 Proceedings of the second annual workshop on Computational learning theory
Learnable classes of categorial grammars

Learnable classes of categorial grammars
Optimal Unification of Infinite Sets of Types

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paperwe explain how to derive learnability of some classes of categorial languages as a consequence of the a property that have unifiable infinite sets of types, namely unification compactness. At first we present an alternate (with respect to [6]) proof of learnability of rigid languages, that introduces our method. Then we prove learnability of the class of semi-rigid languages, which lies in between (learnable) class of rigid languages and (not learnable) class of optimal (as defined by Kanazawa in [6]) languages.