Open AccessProceedings Article
String Extension Learning
Jeffrey Heinz
- 11 Jul 2010
- pp 897-906
49
TL;DR: The authors provides a unified, learning-theoretic analysis of several learnable classes of languages discussed previously in the literature, and provides a recipe for constructing new learnable models for aspects of natural language and cognition.
read more
Abstract: This paper provides a unified, learning-theoretic analysis of several learnable classes of languages discussed previously in the literature. The analysis shows that for these classes an incremental, globally consistent, locally conservative, set-driven learner always exists. Additionally, the analysis provides a recipe for constructing new learnable classes. Potential applications include learnable models for aspects of natural language and cognition.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
Tier-based Strictly Local Constraints for Phonology
Jeffrey Heinz,Chetan Rawal,Herbert G. Tanner +2 more
- 19 Jun 2011
TL;DR: It is found that these languages contain the Strictly Local languages, are star-free, are incomparable with other known sub-star-free classes, and have other interesting properties.
144
Computational Phonology - Part I: Foundations
TL;DR: Computational phonology approaches the study of sound patterns in the world’s languages from a computational perspective and reveals a restrictive, universal property of phonological patterns: they are regular.
Computing Vowel Harmony: The Generative Capacity of Search & Copy
Samuel Andersson,Hossep Dolatian,Yiding Hao +2 more
- 02 May 2020
TL;DR: It is shown that used in its unidirectional mode, all transformations described by an S&C analysis can be modeled by tier-based input strictly local functions (TISL), which improves the previous result of Gainor et al 2012.
References
•Book
Kernel Methods for Pattern Analysis
John Shawe-Taylor,Nello Cristianini +1 more
- 01 Jan 2004
TL;DR: This book provides an easy introduction for students and researchers to the growing field of kernel-based pattern analysis, demonstrating with examples how to handcraft an algorithm or a kernel for a new specific application, and covering all the necessary conceptual and mathematical tools to do so.
Language identification in the limit
TL;DR: It was found that theclass of context-sensitive languages is learnable from an informant, but that not even the class of regular languages is learningable from a text.
3.8K
Learnability and the Vapnik-Chervonenkis dimension
TL;DR: This paper shows that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned.
•Proceedings Article
Text Classification using String Kernels
Huma Lodhi,John Shawe-Taylor,Nello Cristianini,Chris Watkins +3 more
- 01 Jan 2000
TL;DR: In this article, an inner product in the feature space consisting of all subsequences of length k was introduced for comparing two text documents, where a subsequence is any ordered sequence of k characters occurring in the text though not necessarily contiguously.
•Book
Counter-Free Automata
Robert McNaughton,Seymour Papert +1 more
- 15 Nov 1971
TL;DR: A particular class of finite-state automata, christened by the authors "counter-free," is shown here to behave like a good actor: it can drape itself so thoroughly in the notational guise and embed itself so deeply in the conceptual character of several quite different approaches to automata theory that on the surface it is hard to believe that all these roles are being assumed by the same class.
988