en
Proceedings chapter
Open access
English

Modeling the human mental lexicon with self-organizing feature maps

Presented at Twente, May 12-13, 1992
PublisherUniversity of Twente
Publication date1992
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.

Affiliation Not a UNIGE publication
Citation (ISO format)
WITTENBURG, Peter, FRAUENFELDER, Ulrich Hans. Modeling the human mental lexicon with self-organizing feature maps. In: Connectionism and natural language processing. Proceedings of the third Twente Workshop on Language Technology. Twente. [s.l.] : University of Twente, 1992.
Main files (1)
Proceedings chapter (Published version)
accessLevelPublic
Identifiers
  • PID : unige:84384
384views
58downloads

Technical informations

Creation06/02/2016 2:33:00 PM
First validation06/02/2016 2:33:00 PM
Update time03/15/2023 12:26:32 AM
Status update03/15/2023 12:26:32 AM
Last indexation01/16/2024 9:01:30 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack