Chapitre d'actes
previous document  unige:84384  next document
add to browser collection
Title

Modeling the human mental lexicon with self-organizing feature maps

Authors
Wittenburg, Peter
Published in M.F.J. Drossaers & A. Nijholt. Connectionism and natural language processing. Proceedings of the third Twente Workshop on Language Technology. Twente - May 12-13, 1992 - University of Twente. 1992
Abstract Recent efforts to model the remarkable ability of humans to recognize speech and words are described. Different techniques including the use of neural nets for representing phonological similarity between words in the lexicon with self organizing algorithms are discussed. Simulations using the standard Kohonen algorithm are presented to illustrate some problems confronted with this technique in modeling similarity relations of form in the human mental lexicon. Alternative approaches that can potentially deal with some of these limitations are sketched.
Full text
Citation
(ISO format)
WITTENBURG, Peter, FRAUENFELDER, Ulrich Hans. Modeling the human mental lexicon with self-organizing feature maps. In: M.F.J. Drossaers & A. Nijholt (Ed.). Connectionism and natural language processing. Proceedings of the third Twente Workshop on Language Technology. Twente. [s.l.] : University of Twente, 1992. https://archive-ouverte.unige.ch/unige:84384

78 hits

22 downloads

Update

Deposited on : 2016-06-09

Export document
Format :
Citation style :