Mechanical Intelligence: Research and Applications

Abstract

Despite the success of a number of artificial intelligence system as natural-language interfaces to large data bases, the goal of a portable interface remains elusive. A portable interface is defined as a system for understanding natural-language data-base questions that can be easily adapted to a new data base, rather than being hard-wired to the data base for which it was developed. Much of the processing involved in understanding natural-language questions is the same no matter what the form of a particular application's data base. An interface must use many types of knowledge to understand questions: linguistic knowledge about the way words combine to produce meaning, knowledge of the domain of discourse to interpret the question, and knowledge of the structure of the data base to extract relevant data for a reply. Each area of knowledge has a portion that is independent of any particular interface application. For example, it can be argued that much of an interface's knowledge of English syntax is independent of the domain of discourse under consideration. This report identifies application-independent portions of an interface and integrates them with application-dependent portions into a coherent framework. Additional keywords: LADDER(Language Access to Distribute Data with Error Recovery); Man computer interface; ACCAT(Advanced Command and Control Architectural Testbed).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 19, 1979
Accession Number
ADA155417

Entities

People

  • Kurt Konolige

Organizations

  • SRI International

Tags

Communities of Interest

  • C4I
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Ambiguity
  • Artificial Intelligence
  • Command And Control
  • Computer Programming
  • Computer Science
  • Databases
  • English Language
  • Grammars
  • Information Retrieval
  • Information Science
  • Language
  • Natural Languages
  • Semantics
  • Standards
  • Test Sets
  • Translations
  • Translators

Readers

  • Computational Linguistics
  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Software Engineering.

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Translation
  • Fully Networked C3
  • Fully Networked C3 - Command and Control