The ROBOT System: Natural language processing applied to data base query

ABSTRACT

In the early 1970's the natural language processing techniques developed within the field of artificial intelligence (AI) made important progress. Within certain restricted micro worlds of discourse it became possible to process a reasonably large class of English. These techniques have now been applied to the real micro world of data base query, allowing for information to be extracted from data bases by asking ordinary English questions. This paper discusses the importance of true natural language data base query and describes the ROBOT system, a high performance production level system already installed in several real world environments. The specific data structure requirements of the ROBOT system are discussed, as well as an extended type of data inversion that provides precisely the functionality required by the natural language parser.

REFERENCES

• 1: Terry Winograd, Understanding Natural Language, Academic Press, Inc., Orlando, FL, 1972
• 2: Woods, W.A. et al, "The Lunar Sciences Natural Language Information System", BB&N Report 2378, June 1972
• 3: "ADASCRIPT User's Manual", Software AG of North America, Reston, Va.
• 4: "NOMAD Reference Manual", National CSS, Inc., Norwalk, Conn.
• 5: Waltz, D.L., "Natural Language Access to a Large Data Base", Naval Research Report, January 1976
• 6: Hendrix, G. et al, "Developing a natural language interface to complex data", Proceedings of the Third International Conference on Very Large Data Bases, Oct 1977
• 7: Harris, L.R., "User Oriented data base query with the ROBOT natural language query system," International Journal of Man-Machine Studies(1977) 9,pp 697-713
• 8: Harris, L.R., "ROBOT: A High Performance Natural Language Interface for Data Base Query", TR 77-1, Mathematics Department, Dartmouth College
• 9: Harris, L.R., "Natural Language Data Base Query: Using the data base itself as a definition of world knowledge and as an extension of the dictionary", TR 77-2, Mathematics Department, Dartmouth College
• 10: Harris, L.R., "A Model for Adative Problem Solving Applied to Natural Language Acquisition", TR 72-133, Department of Computer Science, Cornell University.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems
          Subjects: Query processing

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing

General Terms:
Languages, Management

Keywords:
Data base query, Natural lanugage