IR-NLI: an expert natural language interface to online data bases
Constructing natural language interfaces to computer systems often requires achievement of advanced reasoning and expert capabilities in addition to basic natural language understanding. In this paper the above issues are faced in the context of an actual application concerning the design of a natural language interface for access to online information retrieval systems. After a short discussion of the peculiarities of this application, which requires both natural language understanding and reasoning capabilities, the general architecture and fundamental design criteria of IR-NLI, a system presently being developed at the University of Udine, are presented. Attention is then focused on the basic functions of IR-NLI, namely, understanding and dialogue, strategy generation, and reasoning. Knowledge representation methods and algorithms adopted are also illustrated. A short example of interaction with IR-NLI is presented. Perspectives and directions for future research are also discussed. 15 references.
- OSTI ID:
- 5342204
- Country of Publication:
- United States
- Language:
- English
Similar Records
Integrating expert systems with solid modeling through interprocess communications and the applications interface specification
Transportable natural-language interfaces: problems and techniques