Contributo in atti di convegno, 2005, ENG, 10.1007/1-4020-3432-6_23

Wordnet and semidiscrete decomposition for sub-symbolic representation of words

Pilato G; Vassallo G; Gaglio S

ICAR; DINFO

A methodology for sub-symbolic semantic encoding of words is presented. The methodology uses the standard, semantically highly-structured WordNet lexical database and the SemiDiscrete matrix Decomposition to obtain a vector representation with low memory requirements in a semantic n-space. The application of the proposed algorithm over all the WordNet words would lead to a useful tool for the sub-symbolic processing of texts.

15th Italian Workshop on Neural Nets (WIRN VETRI 2004), pp. 191–198, Perugia, ITALY, SEP 14-17, 2004

Keywords

CNR authors

Gaglio Salvatore, Pilato Giovanni

CNR institutes

ICAR – Istituto di calcolo e reti ad alte prestazioni