Probabilistic learnability of context-free grammars with basic distributional properties from positive examples

DOI10.1016/J.TCS.2015.10.037zbMath1335.68112OpenAlexW2219332833MaRDI QIDQ5964066

Ryo Yoshinaka, Chihiro Shibata

Publication date: 26 February 2016

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2015.10.037

zbMATH Keywords

PAC learninggrammatical inferencedistributional learning

Mathematics Subject Classification ID

Computational learning theory (68Q32) Formal languages and automata (68Q45) Grammars and rewriting systems (68Q42)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distributional learning of parallel multiple context-free grammars
• The equivalence and inclusion problems for NTS languages
• NTS languages are deterministic and congruential
• Learning regular sets from queries and counterexamples
• Efficient learning of multiple context-free languages with multidimensional substitutability from positive data
• PAC Learning of Some Subclasses of Context-Free Grammars with Basic Distributional Properties from Positive Data
• Integration of the Dual Approaches in the Distributional Learning of Context-Free Grammars
• A Learnable Representation for Syntax Using Residuated Lattices
• Polynomial Time Probabilistic Learning of a Subclass of Linear Languages with Queries
• Identification in the Limit of k,l-Substitutable Context-Free Languages
• PAC-Learning Unambiguous NTS Languages
• Distributional Learning of Some Context-Free Languages with a Minimally Adequate Teacher
• Learning Context Free Grammars with the Syntactic Concept Lattice
• PAC-Learning Unambiguous k,l-NTS ≤  Languages
• A theory of the learnable
• Cryptographic limitations on learning Boolean formulae and finite automata
• Towards Dual Approaches for Learning Context-Free Grammars Based on Syntactic Concept Lattices
• Probability and Computing
• Grammatical Inference: Algorithms and Applications

This page was built for publication: Probabilistic learnability of context-free grammars with basic distributional properties from positive examples