Recognizing the most effective approximate reasoning calculi for a knowledge-based system

An important issue in the design of knowledge-based systems is how to equip them with the capability to transmit uncertainty from imprecise premises to a conclusion. Moreover, an important issue is the identification of the most appropriate calculi. This study compared the effectiveness of various calculi. The test domain was full-text retrieval of natural language documents. This test domain was chosen because natural language is inherently imprecise and there are well defined performance measures to provide the basis of comparison. Both robustness and relative retrieval quality were studied. A robust search will give comparable performance when used by a variety of different users. Retrieval quality measures the quantity and appropriateness of the retrieved information. Of particular interest in the results is that the most commonly used calculi in knowledge-based systems were not the best performing