Abstract: . . .  no processing is deferred beyond the first point at which it could happen. We’re now going to look at the mechanism he builds up, starting with the incredibly beautiful notion of entropy. In the following discussion I rely on (Schneider, 2005). 8 An introduction to entropy Imagine a device D 1 that can emit three symbols A, B, C. • Before D 1 can emit anything, we are uncertain about which symbol among the three possible ones it will emit. We can quantify this uncertainty and say it’s 3. • Now a symbol . . .
. . .  psycholinguistics Page 1 An introduction to computational psycholinguistics : Modeling human sentence processing Shravan Vasishth University of Potsdam, Germany http://www.ling.uni-potsdam.de/~vasishth vasishth@acm.org September 2005, Bochum Probabilistic models: (Crocker & Keller, 2005) • In ambiguous . . .
. . .  psycholinguistics Page 1 An introduction to computational psycholinguistics : Modeling human sentence processing Shravan Vasishth University of Potsdam, Germany http://www.ling.uni-potsdam.de/~vasishth vasishth@acm.org September 2005, Bochum Probabilistic models: (Crocker & Keller, 2005) • In ambiguous sentences, a preferred interpretation . . .
. . .  j ) = 1 (1) 4 • The probability of a parse tree is the product of the rule probabilities. P(t) = Y (N??)?R P(N ? ?) (2) • Jurafsky (1996) has suggested that the probability of a grammar rule models the ease with which the rule can be accessed by the human sentence processor. • Example from Crocker and Keller (2005) shows how this setup can be used to predict parse preferences. • Further reading: Manning and Schutze, and Jurafsky and Martin. • NLTK demo. 5 Page 4 Estimating the rule probabilities and . . .
--2010,4,251,1942,10052