ABSTRACT
The need for Natural Language Interfaces to databases (NLIs) has become increasingly acute as more and more people access information through their web browsers, PDAs, and cell phones. Yet NLIs are only usable if they map natural language questions to SQL queries correctly. As Schneiderman and Norman have argued, people are unwilling to trade reliable and predictable user interfaces for intelligent but unreliable ones. In this paper, we introduce a theoretical framework for reliable NLIs, which is the foundation for the fully implemented Precise NLI. We prove that, for a broad class of semantically tractable natural language questions, Precise is guaranteed to map each question to the corresponding SQL query. We report on experiments testing Precise on several hundred questions drawn from user studies over three benchmark databases. We find that over 80% of the questions are semantically tractable questions, which Precise answers correctly. Precise automatically recognizes the 20% of questions that it cannot handle, and requests a paraphrase. Finally, we show that Precise compares favorably with Mooney's learning NLI and with Microsoft's English Query product
- J. Allen, G. Ferguson, and A. Stent. An architecture for more realistic conversational systems. In Intelligent User Interface, 2001.]] Google ScholarDigital Library
- I. Androutsopoulos, G. D. Ritchie, and P. Thanisch. Natural Language Interfaces to Databases - An Introduction. In Natural Language Engineering, vol 1, part 1, pages 29--81, 1995.]]Google ScholarCross Ref
- F. Baader and B. Hollunder. A Terminological Knowledge Representation System with Complete Inference Algorithms. In Proceedings of the First International Workshop on Processing Declarative Knowledge, 1991.]] Google ScholarDigital Library
- E. Charniak. A Maximum-Entropy-Inspired Parser. In Proceedings of NAACL-2000, 2000.]] Google ScholarDigital Library
- C. Chekuri and A. Rajamaran. Conjunctive Query Containment Revisited. In Proceedings of the Sixth International Conference on Database Theory, 1998.]] Google ScholarDigital Library
- W. Chu and F. Meng. Database Query Formation from Natural Language using Semantic Modeling and Statistical Keyword Meaning Disambiguation. Technical Report 990003, UCLA CS Dept., 16, 1999.]]Google Scholar
- M. Core, J. Moore, and C. Zinn. Initiative in Tutorial Dialogue. In Proceedings of ITS 2002 Workshop on Empirical Methods for Tutorial Dialogue Systems (ITS-02), 2002.]]Google Scholar
- T. Cormen, C. Leiserson, and R. Rivest. Introduction to Algorithms. MIT Press, Cambridge, Massachusetts, 1984.]] Google ScholarDigital Library
- F. Donini, M. Lenzerini, D. Nardi, and W. Nutt. The Complexity of Concept Languages. In Information and Computation, 134, 1997.]] Google ScholarDigital Library
- O. Etzioni, H. Kautz, and A. Popescu. Towards a theory of natural language interfaces to databases. In Submitted for publication, 2002.]]Google Scholar
- B. Grosz, D. Appelt, P. Martin, and F. Pereira. TEAM: An Experiment in the Design of Transportable Natural Language Interfaces. In Artificial Intelligence 32, pages 173--243, 1987.]] Google ScholarDigital Library
- G. Hendrix, E. Sacerdoti, D. Sagalowicz, and J. Slocum. Developing a natural language interface to complex data. In ACM transactions on Database Systems 3(2), pages 105--147, 1978.]] Google ScholarDigital Library
- R. Kittredge. Sublanguages. In American Journal of Computational Linguistics 8(2), pages 79--84, 1982.]] Google ScholarDigital Library
- Kittredge.R. Variation and homogeneity of sublanguages. In R. Kittredge and J. Lehrberger, editors, Sublanguage: Studies of Language in Restricted Semantic Domains, pages 107--137. de Gruyter, Berlin, 1982.]]Google Scholar
- G. R. Adaptive information extraction and sublanguage analysis. In Proceedings of IJCAI 2001, 2001.]]Google Scholar
- S. Satingh, D. Litman, M. Kearns, and M. Walker. Optimizing Dialogue Management With Reinforcement Learning: Experiments with the NJFun System. In Journal of Artificial Intelligence Research (JAIR), 2002.]]Google Scholar
- S. Satoshi. A New Direction For Sublanguage Nlp. In New Methods in Language Processing, pages 165--177, 1997.]]Google Scholar
- D. Stallard. A terminological transformation for natural language question-answering systems. In Proceedings of ACL-86, 1986.]] Google ScholarDigital Library
- L. Tang and R. Mooney. Using Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing. In Proceedings of the 12th European Conference on Machine Learning (ECML-2001), Freiburg, Germany, pages 466--477, 2001.]] Google ScholarDigital Library
- T. Uno. Algorithms for Enumerating All Perfect, Maximum and Maximal Matchings in Bipartite Graphs. In International Symposium on Algorithms and Computation (ISAAC 1997), pages 92--101, 1997.]] Google ScholarDigital Library
- L. Valiant. A Theory of the Learnable. In Communications of the ACM, v27 n.11, pages 1134--1142, 1984.]] Google ScholarDigital Library
- A. Yates, O. Etzioni, and D. Weld. A Reliable Natural Language Interface to Household Appliances. In Submitted to IUI-2003, 2002.]] Google ScholarDigital Library
Index Terms
- Towards a theory of natural language interfaces to databases
Recommendations
Towards a theory of natural language interfaces to databases
IUI '03: Proceedings of the 8th international conference on Intelligent user interfacesThe need for Natural Language Interfaces (NLIs) to databases has become increasingly acute as more nontechnical people access information through their web browsers, PDAs and cell phones. Yet NLIs are only usable if they map natural language questions ...
Interactive natural language interface
To override the complexity of SQL, and to facilitate the manipulation of data in databases for common people (not SQL professionals), many researches have turned out to use natural language instead of SQL. The idea of using natural language instead of ...
Generic interactive natural language interface to databases (GINLIDB)
EC'09: Proceedings of the 10th WSEAS international conference on evolutionary computingTo override the complexity of SQL, and to facilitate the manipulation of data in databases for common people (not SQL professionals), many researches have turned out to use natural language instead of SQL. The idea of using natural language instead of ...
Comments