Natural Language Database Access Using Semi-automatically Constructed Translation Knowledge
In most natural language database interfaces (NLDBI), translation knowledge acquisition heavily depends on human specialties, consequently undermining domain portability. This paper attempts to semi-automatically construct translation knowledge by introducing a physical Entity-Relationship schema, and by simplifying translation knowledge structures. Based on this semi-automatically produced translation knowledge, a noun translation method is proposed in order to resolve NLDBI translation ambiguities.
KeywordsTranslation Knowledge Domain Class Class Term Case Marker User Question
Unable to display preview. Download preview PDF.
- 1.Androutsopoulos, I.: Interfacing a Natural Language Front-End to Relational Database. Master.s thesis, Technical Report 11, Department of Artificial Intelligence, University of Edinburgh (1993)Google Scholar
- 9.Meng, F., Chu, W.W.: Database Query Formation from Natural Language using Semantic Modeling and Statistical Keyword Meaning Disambiguation. Technical Report, CSD-TR 990003,University of California, Los Angeles (1999)Google Scholar
- 10.Salton, G., McGill, M.J.: An Introduction to Modern Information Retrieval. McGraw-Hill, New York (1983)Google Scholar
- 11.Wallace, M.: Communicating with Databases in Natural Language. Ellis Horwood, Chichester (1984)Google Scholar
- 13.Warren, D., Pereira, F.: An Efficient Easily Adaptable System for Interpreting Natural Language Queries. Computational Linguistics 8(3-4), 110–122 (1982)Google Scholar