NATURAL LANGUAGE LEARNING BY COMPUTER

Abstract

Learning a natural language is taken as an improvement in a system's ability to express situations in a natural language. This dissertation describes a computer program, called Zbie, written in IPL-V, which accepts the description of situations in a uniform, structured functional language and tries to express these situations in a natural language. Examples are given for German and, mostly, Russian. At run-time, Zbie builds simple memory structures. Patterns and sets are built on the functional language. The translation rules of the patterns and an in-context vocabulary provide the transition to the natural language. Zbie is a cautious learner, and avoids errors by several mechanisms. Zbie is capable of some evolutionary learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1968
Accession Number
AD0671937

Entities

People

  • Laurent Siklossy

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence
  • Behavioral Sciences
  • Books
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Grammars
  • Language
  • Linguistics
  • Natural Languages
  • New York
  • Psychology
  • Scientific Research
  • Semantics
  • Translations

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Systems Analysis and Design