Theory of conceptual dependence is a model of natural language understanding used in artificial intelligence systems.
Roger Schank at Stanford University introduced the model in 1969, in the early days of artificial intelligence. This model is widely used by Schank students at Yale University such as Robert Wilensky, Wendy Lehnert, and Janet Kolodner.
Schank developed a model to represent knowledge for natural language input to a computer. Partly influenced by the work of Sydney Lamb, the goal is to make the independent meaning of the words used in the input, ie two sentences identical in meaning, will have a single representation. This system is also intended to draw a logical conclusion.
The model uses the following basic representational tokens:
-
- real world objects , each with some attributes .
- real-world action , each with an attribute
- times
- location
A series of concept transitions then act on this representation, e.g. ATRANS are used to represent transfers such as "give" or "take" while PTRANS is used to act on locations such as "moving" or "going". MTRANS represent mental acts like "know", etc.
A phrase like "John gives a book to Mary" is then represented as an ATRAN action on two real-world objects, John and Mary.
Video Conceptual dependency theory
See also
- Augmented transition network
- Scripts (artificial intelligence)
Maps Conceptual dependency theory
References
External links
- Lytinen, S.L. (1992) "Conceptual and Derived Dependence" Computers, Mathematics, and Applications 23 (2-5): 51-73
Source of the article : Wikipedia
0 Comments