Towards Understanding of Natural Language: Neurocognitive Inspirations

Wlodzislaw Duch1,2, Pawel Matykiewicz1,3, John Pestian3
1Department of Informatics, Nicolaus Copernicus University, Grudziadzka 5, 87-100 Torun, Poland.
2School of Computer Engineering, Nanyang Technological University, Singapore.
3Department of Biomedical Informatics, Children's Hospital Research Foundation, Cincinnati, Ohio, USA, and


Neurocognitive processes responsible for representation of meaning and understanding of words are investigated. First a review of current knowledge on word representation is presented, recent experiments linking it to asso-ciative memory and to right hemisphere synchronous activity is analyzed, and various conjectures on how meaning arises and how reasoning and problem solving is done are presented. These inspirations are used to make systematic approximation to spreading activation in semantic memory networks. Using hierarchical ontologies representations of short texts are enhanced and it is shown that high-dimensional vector models may be treated as a snapshot approximation of the neural activity. Clusterization of short medical texts that may be assigned to different categories is greatly enhanced by this process, facilitating understanding of the text.

J. Marques de Sá et al. (Eds.): ICANN, Part II, Springer-Verlag LNCS 4669, pp. 953–962, 2007

Preprint for comments in PDF, 227 KB.

BACK to the publications of W. Duch.
BACK to the on-line publications of the Department of Informatics, NCU.