Referenzsemantik in der Partnermodellierung

How can we explain that an assertion on something perceived can be understood in the same manner by somebody who cannot perceive that scene? This problem bases the interest in computational linguistics in how listener modeling could possibly be harmonized with reference semantics. Mental images substituting real perception appear as a way out. The architecture of the listener model has to be adapted to the creation and use of such pictorial data structures. Furthermore, the relation between the latter and a verbal (i. e., propositional) representation must be understood. The resulting architecture of a listener model with reference semantics can be employed to solve communicational problems from three general classes in a better way, as is demonstrated by an example implementation.     

Reliability of multiple classifications

Cohen's kappa index is reformulated for multiple classifications based on exchangeable random variables. It is found that kappa is between 0 and 1 inclusive. Two characterizations for kappa are stated in terms of the relationship between such random variables. Within the normal test score model, kappa increases with test reliability and test length. Furthermore, when based on binary classifications, kappa is an inverse U-shaped function of the cutoff score. These trends also hold for the beta-binomial test score model.Paper read at the Spring meeting of the Psychometric Society, Bell Laboratories (Murray Hill, New Jersey), March 1976.The editorial assistance and helpful comments of Leonard S. Feldt, Sarah P. Seaman-Huynh, and the three referees are gratefully acknowledged.     

Two simple classes of mastery scores based on the beta-binomial model

Two simple classes of mastery scores which are suitable for hand calculations are presented for beta-binomial test score distributions combined with linear and cubic referral success. The models provide a simple way to explore the consequences of selecting an arbitrary mastery score. Such assessment would be useful whenever the test user is not willing to posta priori a loss ratio, but wishes to look at the various consequences before aiming at a particular score.