Freydenberger_Reidenbach_COLT_2010[1].pdf (256.93 kB)
0/0

Inferring descriptive generalisations of formal languages

Download (256.93 kB)
conference contribution
posted on 06.07.2010 by Dominik Freydenberger, Daniel Reidenbach
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 Angluin’s corresponding result for exact inference. 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 deep insights of intrinsic interest into combinatorial and algorithmic properties of pattern languages.

History

School

  • Science

Department

  • Computer Science

Citation

FREYDENBERGER, D.D. and REIDENBACH, D., 2010. Inferring descriptive generalisations of formal languages. IN: Kalai, A.T. and Mohri, M. (eds). COLT 2010: Proceedings of the 23rd Conference on Learning Theory, Haifa, Israel, June 27-29, 2010. Madison, Wisconsin : OmniPress, pp. 194-206.

Publisher

OmniPress for the Association for Computational Learning (ACL) / © The authors

Version

AM (Accepted Manuscript)

Publication date

2010

Notes

This conference paper is also freely available online from: http://www.colt2010.org/proceedings.html

ISBN

9780982252925

Language

en

Exports

Logo branding

Keyword(s)

Exports