Issues in Translating from Natural Language to SQL in a Domain-Independent Natural Language Interface to Databases
This paper deals with a domain-independent natural language interface to databases (NLIDB) for the Spanish language. This NLIDB had been previously tested for the Northwind and Pubs domains and had attained good performance (86% success rate). However, domain independence complicates the task of achieving high translation success, and to this end the ATIS (Air Travel Information System) database, which has been used by several natural language interfaces, was selected to conduct a new evaluation. The purpose of this evaluation was to asses the efficiency of the interface after the reconfiguration for another domain and to detect the problems that affect translation success. For the tests a corpus of queries was gathered and the results obtained showed that the interface can easily be reconfigured and that attained a 50% success rate. When the found problems concerning query translation were analyzed, wording deficiencies of some user queries and several errors in the synonym dictionary were discovered. After correcting these problems a second test was conducted, in which the interface attained a 61.4% success rate. These experiments showed that user training is necessary as well as a dialogue system that permits to clarify a query when it is deficiently formulated.
KeywordsDialogue System Structure Query Language Fare Class Noun Location Natural Language Interface
Unable to display preview. Download preview PDF.
- 1.Androutsopoulos, I., Ritchie, G.D., Thanisch, P.: Natural Language Interfaces to DataBases - An Introduction. Department of Artificial Intelligence, University of Edinburgh (1995)Google Scholar
- 2.Pazos, R., Pérez, O.J., González, B.J., Gelbukh, A.F., Sidorov, G., Rodríguez, M.M.: A Domain Independent Natural Language Interface to Databases Capable of Processing Complex Queries. In: Gelbukh, A., de Albornoz, Á., Terashima-Marín, H. (eds.) MICAI 2005. LNCS (LNAI), vol. 3789, pp. 833–842. Springer, Heidelberg (2005)CrossRefGoogle Scholar
- 4.Montero, J.M.: Sistemas de conversión texto voz. B.S.thesis. Universidad Polit, http://lorien.die.upm.es/~juancho
- 5.Ward, W.: Evaluation of the CMU ATIS System. In: Proc. DARPA Speech and Natural Language Workshop, pp. 101–105 (1991)Google Scholar
- 6.Zue, V., Glass, J., Goodine, D., Leung, H., Philips, M., Polifroni, J., Seneff, S.: Preliminary ATIS Development MIT. In: Proc. DARPA Speech and Natural Language Workshop, pp. 130–135 (1990)Google Scholar
- 7.Kubala, F., Austin, S., Barry, C., Makhoul, J., Placeway, P., Schwartz, R.: BYBLOS Speech Recognition Benchmark Results. In: Proc. Workshop on Speech and Natural Language, pp. 77–82 (1991)Google Scholar
- 8.Pieraccini, R., Tzoukermann, E., Gorelov, Z., Levin, E., Lee, C., Gauvain, J.: Progress Report on the Chronus System: ATIS Benchmark Results (1992)Google Scholar
- 9.Popescu, A.M., Armanasu, A., Etzioni, O., Ko, D., Yates, A.: Modern Natural Language Interfaces to Databases: Composing Statical Parsing with Semantic Tractability. University of Washington (2004)Google Scholar
- 13.Microsoft English Query Tutorials available with standard installation in SQL SERVER 7.0Google Scholar