The Structure of a Semantic Neural Network Realizing Morphological and Syntactic Analysis of a Text

  • Authors:
  • D. E. Shuklin

  • Affiliations:
  • Kharkov State Technical University of Radioelectronics, Ministry of Education of Ukraine, Kharkov, Ukraine

  • Venue:
  • Cybernetics and Systems Analysis
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

A synchronized linear tree is considered as the structure of connections between neurons in a semantic neural network, which makes it possible to perform operations of morphological and syntactic analysis. Such a tree can be considered as a finite automaton. A dictionary entry is realized by a neural subautomaton. Wordforms of a dictionary entry are substates of such a subautomaton. An inflection consists of the transition of the subautomaton from one substate to another.