On Sufficient Conditions to Identify in the Limit Classes of Grammars from Polynomial Time and Data

Authors:
Colin De La Higuera;José Oncina
Affiliations:
-;-
Venue:
ICGI '02 Proceedings of the 6th International Colloquium on Grammatical Inference: Algorithms and Applications
Year:
2002

Citing 17
Cited 3

A theory of the learnable

Communications of the ACM
Grammatical interface for even linear languages based on control sets

Information Processing Letters
Crytographic limitations on learning Boolean formulae and finite automata

STOC '89 Proceedings of the twenty-first annual ACM symposium on Theory of computing
Learning context-free grammars from structural data in polynomial time

Theoretical Computer Science
The minimum consistent DFA problem cannot be approximated within any polynomial

Journal of the ACM (JACM)
An efficient probabilistic context-free parsing algorithm that computes prefix probabilities

Computational Linguistics
How many queries are needed to learn?

Journal of the ACM (JACM)
Characteristic Sets for Polynomial Grammatical Inference

Machine Learning
Recent advances of grammatical inference

Theoretical Computer Science - Special issue on algorithmic learning theory
Results of the Abbadingo One DFA Learning Competition and a New Evidence-Driven State Merging Algorithm

ICGI '98 Proceedings of the 4th International Colloquium on Grammatical Inference
Pattern Discovery in Biosequences

ICGI '98 Proceedings of the 4th International Colloquium on Grammatical Inference
Learning XML Grammars

MLDM '01 Proceedings of the Second International Workshop on Machine Learning and Data Mining in Pattern Recognition
Inductive Inference, DFAs, and Computational Complexity

AII '89 Proceedings of the International Workshop on Analogical and Inductive Inference
Identification of Function Distinguishable Languages

ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
Queries Revisited

ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Inferring Deterministic Linear Languages

COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
A Characterization of Even Linear Languages and its Application to the Learning Problem

ICGI '94 Proceedings of the Second International Colloquium on Grammatical Inference and Applications

The degree of parallelism

Journal of Automata, Languages and Combinatorics
Language structure using fuzzy similarity

IEEE Transactions on Fuzzy Systems
A bibliographical study of grammatical inference

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

Linearity and determinism seem to be two essential conditions for polynomial learning of grammars to be possible. We propose a general condition valid for certain subclasses of the linear grammars given which these classes can be polynomially identified in the limit from given data. This enables us to give new proofs of the identification of well known classes of grammars, and to propose a new (and larger) class of linear grammars for which polynomial identification is thus possible.