Extracting finite structure from infinite language

De Montfort University Open Research Archive

Show simple item record

dc.contributor.author Hopgood, Adrian A. en
dc.contributor.author McQueen, T. A. en
dc.contributor.author Allen, T. J. en
dc.contributor.author Tepper, J. A. en
dc.date.accessioned 2008-11-24T13:24:17Z
dc.date.available 2008-11-24T13:24:17Z
dc.date.issued 2005-08-01 en
dc.identifier.citation McQueen, T. et al. (2005) Extracting finite structure from infinite language. Knowledge-Based Systems, 18(4-5), pp. 135-141.
dc.identifier.issn 0950-7051 en
dc.identifier.uri http://hdl.handle.net/2086/196
dc.description This paper presents a novel unsupervised neural network model for learning the finite-state properties of an input language from a set of positive examples. The model is demonstrated to learn the Reber grammar perfectly from a randomly generated training set and to generalize to sequences beyond the length of those found in the training set. Crucially, it does not require negative examples. 30% of the tests yielded perfect grammar recognizers, compared with only 2% reported by other authors for simple recurrent networks. The paper was initially presented at AI-2004 conference where it won the Best Technical Paper award. en
dc.language.iso en en
dc.publisher Elsevier en
dc.subject RAE 2008
dc.subject UoA 23 Computer Science and Informatics
dc.subject artificial neural networks
dc.subject grammar induction
dc.subject natural language processing
dc.subject self-organizing map
dc.subject STORM (Spatio Temporal Self-Organizing Recurrent Map)
dc.title Extracting finite structure from infinite language en
dc.type Article en
dc.identifier.doi http://dx.doi.org/10.1016/j.knosys.2004.10.010 en
dc.researchgroup Centre for Computational Intelligence


Files in this item

This item appears in the following Collection(s)

Show simple item record