A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries

  • Rodolfo A. Pazos Rangel
  • O. Joaquín Pérez
  • B. Juan Javier González
  • Alexander Gelbukh
  • Grigori Sidorov
  • M. Myriam J. Rodríguez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3789)

Abstract

We present a method for creating natural language interfaces to databases (NLIDB) that allow for translating natural language queries into SQL. The method is domain independent, i.e., it avoids the tedious process of configuring the NLIDB for a given domain. We automatically generate the domain dictionary for query translation using semantic metadata of the database. Our semantic representation of a query is a graph including information from database metadata. The query is translated taking into account the parts of speech of its words (obtained with some linguistic processing). Specifically, unlike most existing NLIDBs, we take seriously auxiliary words (prepositions and conjunctions) as set theory operators, which allows for processing more complex queries. Experimental results (conducted on two Spanish databases from different domains) show that treatment of auxiliary words improves correctness of translation by 12.1%. With the developed NLIDB 82of queries were correctly translated (and thus answered). Reconfiguring the NLIDB from one domain to the other took only ten minutes.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Popescu, A.M., Etzioni, O., Kautz, H.: Towards a Theory of Natural Language Interfaces to Databases. In: Proceedings of the 2003 International Conference on Intelligent User Interfaces. ACM Press, New York (2003)Google Scholar
  2. 2.
    Zarate, A., Pazos, R., Gelbukh, A., Padrón, I.: A Portable Natural Language Interface for Diverse Databases Using Ontologies. In: Gelbukh, A. (ed.) CICLing 2003. LNCS, vol. 2588. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  3. 3.
    Stallard, M.S., Bobrow, D., Schwartz, R.: A Fully Statistical Approach to Natural Language Interfaces. In: Proc. 34th Annual Meeting of the Association for Computational Linguistics (1996), http://citeseer.nj.nec.com/miller96fully.html
  4. 4.
    Minker, W.: Stochastically-Based Natural Language Understanding across Task and Languages. In: Proc. of EuroSpeech 1997, Rodas, Greece (1997), http://citeseer.nj.nec.com/minker97stochasticallybased.html
  5. 5.
    Moreno, L., Molina, A.: Preliminares y Tendencias en el Procesamiento del Lenguaje Natural. Departamento de Sistemas Informáticos y Computación. Universidad Politécnica de Valencia, http://www3.unileon.es/dp/dfh/Milka/MR99b.pdf
  6. 6.
    Meng, F., Chu, W.W.: Database Query Formation from Natural Language Using Semantic Modeling and Statistical Keyword Meaning Disambiguation. Computer Science Department. University of California, http://www.cobase.cs.ucla.edu/tech-docs/ucla-990003.ps
  7. 7.
    InBase-Online. English Queries to Personnel DB. Russian Research Institute of Artificial Intelligence (2001), http://www.inbase.artint.ru/nl/kadry-eng.asp
  8. 8.
    Montero, J.M.: Sistemas de Conversión Texto Voz. B.S. thesis. Universidad Politécnica de Madrid, http://lorien.die.upm.es/juancho
  9. 9.
    Sethi, V.: Natural Language Interfaces to Databases: MSI Impact, and Survey of their Use and Importance, University of Pittsburgh (1986)Google Scholar
  10. 10.
    AVENTINUS - Advanced Information System for Multinational Drug Enforcement, http://www.dcs.shef.ac.uk/nlp/funded/aventinus.html
  11. 11.
    Sidorov, G.: Problemas Actuales de Lingüística Computacional. Revista Digital Universitaria 2(1) (2001), http://www.revista.unam.mx/vol.2/num1/art1
  12. 12.
    Stratica, N., Kosseim, L., Desai, B.: NLIDB Templates for Semantics Parsing. In: Proceedings of Applications of Natural Language to Data Bases (NLDB 2003), pp. 235–241 (2003), http://www.cs.concordia.ca/kosseim/research.html
  13. 13.
    ELF Software Co.: Results from the Head to Head Competition (2001), http://elf-soft.com/ns/demos.htm
  14. 14.
    Real Academia Española: Gramática Descriptiva de la Lengua Española. Espasa Calpe (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Rodolfo A. Pazos Rangel
    • 1
  • O. Joaquín Pérez
    • 1
  • B. Juan Javier González
    • 2
  • Alexander Gelbukh
    • 3
  • Grigori Sidorov
    • 3
  • M. Myriam J. Rodríguez
    • 2
  1. 1.National Center for Investigation and Technological Development (CENIDET) 
  2. 2.Technological Institute of Cd. MaderoMéxico
  3. 3.Center for Computing Research(CIC)National Polytechnic Institute(IPN)México

Personalised recommendations