Problems in Natural-Language Interface to DBMS With Examples From EUFID

For five years the End-User Friendly Interface to Data management (EUFID) project team at System Development Corporation worked on the design and implementation of a Natural-Language Interface (NLI) system that was to be independent of both the application and the database management system. In this paper we describe application, natural-language and database management problems involved in NLI development, with specific reference to the EUFID system as an example.

[1]  John F. Burger.  Semantic database mapping in EUFID , 1980, SIGMOD '80.

[2]  Robert F. Simmons,et al.  Answering English questions by computer: a survey , 1965, CACM.

[3]  Alfred V. Aho,et al.  The Theory of Parsing, Translation, and Compiling , 1972 .

[4]  Remko J. H. Scha,et al.  Philips question-answering system PHLIQA1 , 1977, SGAR.

[5]  Michael Stonebraker,et al.  The design and implementation of INGRES , 1976, TODS.

[6]  Marjorie Templeton.  EUFID: A Friendly and Flexible Front-End For Data Management Systems , 1979, ACL.

[7]  Gary G. Hendrix,et al.  Developing a natural language interface to complex data , 1977, TODS.

[8]  Charles Kellogg,et al.  The converse natural language data management system: current status and plans , 1971, SIGIR '71.

[9]  John K. Tsotsos,et al.  TORUS: a step towards bridging the gap between data bases and the casual user , 1976, Inf. Syst..

[10]  David L. Waltz,et al.  An English language question answering system for a large relational database , 1978, CACM.

[11]  David L. Waltz,et al.  Natural language interfaces , 1977, SGAR.

[12]  C. J. Date.  An Introduction to Database Systems , 1975 .

[13]  Larry R. Harris,et al.  The ROBOT System: Natural language processing applied to data base query , 1978, ACM Annual Conference.

[14]  F. B. Thompson,et al.  REL: A Rapidly Extensible Language system , 1969, ACM '69.

[15]  E. F. Codd,et al.  Seven Steps to Rendezvous with the Casual User , 1974, IFIP Working Conference Data Base Management.