Spectral learning of weighted automata. A forward-backward perspective

DOI10.1007/S10994-013-5416-XMaRDI QIDQ479459zbMATH OpenOpenAlexFDO

Authors Borja Balle, Xavier Carreras, Franco M. Luque, Ariadna Quattoni

Publication date 5 December 2014

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-013-5416-x

zbMATH Keywords

dependency parsingspectral learningweighted finite automata

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Computational learning theory (68Q32)

Recommendations

• On the Rademacher complexity of weighted automata
• A Canonical Form for Weighted Automata and Applications to Approximate Minimization
• Learning weighted automata
• Weighted automata are compact and actively learnable
• Spectral learning of latent-variable PCFGs: algorithms and sample complexity

Cites work

• scientific article; zbMATH DE number 5957212 (Why is no real title available?)
• scientific article; zbMATH DE number 5969142 (Why is no real title available?)
• scientific article; zbMATH DE number 41838 (Why is no real title available?)
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 3588051 (Why is no real title available?)
• scientific article; zbMATH DE number 2243356 (Why is no real title available?)
• A Spectral Approach for Probabilistic Grammatical Inference on Trees
• A theory of the learnable
• Bilexical grammars and their cubic-time parsing algorithms
• Internal structures in \(n\)-permutable varieties
• Introduction to Information Retrieval
• Learning functions represented as multiplicity automata
• Learning probabilistic automata: a study in state distinguishability
• Matrices de Hankel
• On rational stochastic languages
• On the definition of a family of automata
• On the learnability and usage of acyclic probabilistic finite automata
• On the learnability of discrete distributions
• PAC-learnability of probabilistic deterministic finite state automata in terms of variation distance
• Realizations by stochastic finite automata
• Tensor decompositions for learning latent variable models
• Towards Feasible PAC-Learning of Probabilistic Deterministic Finite Automata
• Weighted automata algorithms

Cited in

(11)

• Learning and planning in partially observable environments without prior domain knowledge
• Dimension-free concentration bounds on Hankel matrices for spectral learning
• Singular value automata and approximate minimization
• Learning weighted automata
• Spectral learning of latent-variable PCFGs: algorithms and sample complexity
• Approximate minimization of weighted tree automata
• Bisimulation metrics and norms for real-weighted automata
• PDFA distillation with error bound guarantees
• Generalization bounds for learning weighted automata
• On the Rademacher complexity of weighted automata
• Recognizable series on graphs and hypergraphs

Describes a project that uses

Uses Software

• Penn Treebank

This page was built for publication: Spectral learning of weighted automata. A forward-backward perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q479459)