Identification of unions of languages drawn from an identifiable class
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Polynomial-time learning of very simple grammars from positive data
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
The correct definition of finite elasticity: corrigendum to identification of unions
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
Handbook of formal languages, vol. 3
Learning Local Languages and Their Application to DNA Sequence Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Characteristic sets for polynominal grammatical inference
ICG! '96 Proceedings of the 3rd International Colloquium on Grammatical Inference: Learning Syntax from Sentences
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
Generating all permutations by context-free grammars in Chomsky normal form
Theoretical Computer Science - Algebraic methods in language processing
Languages as hyperplanes: grammatical inference with string kernels
ECML'06 Proceedings of the 17th European conference on Machine Learning
Learning Commutative Regular Languages
ICGI '08 Proceedings of the 9th international colloquium on Grammatical Inference: Algorithms and Applications
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Languages as hyperplanes: grammatical inference with string kernels
ECML'06 Proceedings of the 17th European conference on Machine Learning
Some Alternatives to Parikh Matrices Using String Kernels
Fundamenta Informaticae
Semantic separator learning and its applications in unsupervised Chinese text parsing
Frontiers of Computer Science: Selected Publications from Chinese Universities
| Hi-index | 0.00 |
Strings can be mapped into Hilbert spaces using feature maps such as the Parikh map. Languages can then be defined as the pre-image of hyperplanes in the feature space, rather than using grammars or automata. These are the planar languages. In this paper we show that using techniques from kernel-based learning, we can represent and efficiently learn, from positive data alone, various linguistically interesting context-sensitive languages. In particular we show that the cross-serial dependencies in Swiss German, that established the non-context-freeness of natural language, are learnable using a standard kernel. We demonstrate the polynomial-time identifiability in the limit of these classes, and discuss some language theoretic properties of these classes, and their relationship to the choice of kernel/feature map.