Abstract
We present a seven step model for the successful development of natural language information systems. Its central component is the empirical collection of realistic test data in order to cover all relevant linguistic phenomena, a basic requirement for later wide user acceptance. We also deal with the problem of missing integration in existing natural language front-ends by introducing the Integrated Deductive Approach. Hereby we achieve a consistent mapping of the semantic representation of the user input to the corresponding semantic application model. We apply the model to a case study, the design and implemenation of a distance education system for the reference language Japanese. In this application domain the system has to cope with high
linguistic complexity and variability of input as well as with a widespread community of casual users.
| Original language | German (Austria) |
|---|---|
| Number of pages | 15 |
| Publication status | Published - May 1996 |
Fields of science
- 102001 Artificial intelligence
- 102006 Computer supported cooperative work (CSCW)
- 102010 Database systems
- 102014 Information design
- 102015 Information systems
- 102016 IT security
- 102028 Knowledge engineering
- 102019 Machine learning
- 102022 Software development
- 102025 Distributed systems
- 502007 E-commerce
- 505002 Data protection
- 506002 E-government
- 509018 Knowledge management
- 202007 Computer integrated manufacturing (CIM)
- 102033 Data mining
- 102035 Data science
