Skip to search formSkip to main contentSkip to account menu
Languages as Hyperplanes: Grammatical Inference with String Kernels
TLDR
It is demonstrated that some mildly context sensitive languages can be represented in this way and it is possible to efficiently learn these using kernel PCA, and a new family of grammatical inference algorithms based on this idea are presented.
View via Publisher
Consistent Identification in the Limit of Any of the Classes k -Valued Is NP-hard
TLDR
It is shown that learning any (except one) class from this family by means of a consistent learning function is NP-hard as well.
View via Publisher
Consistent Identification in the Limit of Rigid Grammars from Strings Is NP-hard
TLDR
It is shown that the learning functions for these learnable classes are all NP-hard.
View via Publisher
Proceedings of the European Conference on Machine Learning (ECML)
Planar Languages and Learnability
TLDR
This paper shows that using techniques from kernel-based learning, various linguistically interesting context-sensitive languages can represent and efficiently learn, from positive data alone, various language theoretic properties, and their relationship to the choice of kernel/feature map.
View via Publisher
A Note on the Complexity of Associative-Commutative Lambek Calculus
TLDR
The NP-completeness of the system LP (associative-commutative Lambek calculus) will be shown, and it is shown that this result can be strengthened: LP remains NP-complete under certain restrictions.
View Paper
Naive Infinite Enumeration of Context-free Languages in Incremental Polynomial Time
We consider the naive bottom-up concatenation scheme for a con- text-free language and show that this scheme has the incremental polynomial time property. This means that all members of the language…
View Paper
Learning categorial grammars
TLDR
The main conclusions are: - formal learning theory is relevant to linguistics, - identification in the limit is feasible for non-trivial classes, and the `Shinohara approach' can lead to a learnable class, but this completely depends on the specific nature of the formalism and the notion of complexity.
Consistent identification in the limit of some of Penn and Buszkowski's classes is NP-hard
View Paper
Regular inference as vertex coloring
View via Publisher
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License