A Phrasal Approach to Natural Language Interfaces over Databases

  • Michael Minock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3513)


This short paper introduces the STEP system for natural language access to relational databases. In contrast to most work in the area, STEP adopts a phrasal approach; an administrator couples phrasal patterns to elementary expressions of tuple relational calculus. This ‘phrasal lexicon’ is used bi-directionally, enabling the generation of natural language from tuple relational calculus and the inverse parsing of natural language to tuple calculus. This ability to both understand and generate natural language enables STEP to engage the user in clarification dialogs when the parse of their query is of questionable quality or is open to multiple interpretations. An on-line demonstration of STEP is accessible at


Natural Language Relational Database Inference Rule Relational Query Input Sentence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Androutsopoulos, I., Ritchie, G.D.: Database interfaces. In: Dale, R., Moisl, H., Somers, H. (eds.) Handbook of Natural Language Processing, pp. 209–240. Marcel Dekker Inc., New York (2000)Google Scholar
  2. 2.
    Blum, A.: Microsoft english query 7.5: Automatic extraction of semantics from relational databases and OLAP cubes. In: Proc. of VLDB, pp. 247–248 (1999)Google Scholar
  3. 3.
    Codd, E.: Seven steps to rendezvous with the casual user. In: IFIP Working Conference Data Base Management, pp. 179–200 (1974)Google Scholar
  4. 4.
    Copestake, A., Sparck Jones, K.: Natural language interfaces to databases. The Natural Language Review 5(4), 225–249 (1990)Google Scholar
  5. 5.
    Grosz, B., Appelt, D., Martin, P., Pereira, F.: Team: An experiment in the design of transportable natural-language interfaces. AI 32(2), 173–243 (1987)Google Scholar
  6. 6.
    Ljungberg, J.: Paraphrasing SQL to natural language. In: Proc. of RIAO 1991, Barcelona (1991)Google Scholar
  7. 7.
    Lowden, B., de Roeck, A.: The REMIT system for paraphrasing relational query expressions into natural language. In: Proc. of VLDB, pp. 365–371 (1986)Google Scholar
  8. 8.
    May, W.: Information extraction and integration with Florid: The Mondial case study. Technical Report 131, Universität Freiburg, Institut für Informatik (1999) Google Scholar
  9. 9.
    Miller, G., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.: Five papers on WordNet. Technical report, Princeton University, Princeton, N.J. (1993)Google Scholar
  10. 10.
    Minock, M.: Knowledge representation using schema tuple queries. In: Proc. of KRDB, Hamburg, Germany, pp. 51–62. IEEE Computer Society Press, Hamburg (2003)Google Scholar
  11. 11.
    Minock, M.: Modular generation of relational query paraphrases. Journal of Language and Computation special issue on Formal Aspects of NLG (2005) (to appear)Google Scholar
  12. 12.
    Minock, M.: A phrasal approach to natural language access over relational databases. Technical Report 05.09, Umeå University, Umeå, Sweden (March 2005) Google Scholar
  13. 13.
    Popescu, A., Etzioni, O., Kautz, H.: Towards a theory of natural language interfaces to databases. In: Intelligent User Interfaces (2003)Google Scholar
  14. 14.
    Thalheim, B., Kobienia, T.: Generating DB queries for web NL requests using schema information and DB content. In: Proc. of NLDB, pp. 205–209 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Michael Minock
    • 1
  1. 1.Department of Computing ScienceUmeå UniversitySweden

Personalised recommendations