Context-Free Parsing in Connectionist Networks.

Abstract

This paper presents a simple algorithm which converts any context-free grammar (without epsilon productions) into a connectionist network which parses strings (of arbitrary but fixed maximum length) in the language defined by that grammar. The network is fast and deterministic. Some modifications of the network are also explored, including parsing near misses, disambiguating and learning new productions dynamically. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 30, 1985
Accession Number
ADA170349

Entities

People

  • Mark Fanty

Organizations

  • University of Rochester

Tags

DTIC Thesaurus Topics

  • Acquisition
  • Algorithms
  • Automata Theory
  • Cognitive Science
  • Computer Programming
  • Computer Science
  • Computers
  • Context Free Grammars
  • Grammars
  • Information Systems
  • Language
  • Natural Languages
  • Neural Networks
  • New York
  • Nodes
  • Simulations
  • Simulators

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Networking
  • Mathematical Modeling and Probability Theory.