Abstract

this paper, an estimator is unbiased iff P E # # (#(X)) = P # # for all # , i.e., its expected parameter estimate specifies the same distribution as the true parameters. Similarly, the loss function is mean squared difference between the "true" and estimated distributions, i.e., if# is the event space (in DOP1, the space of all phrase-structure trees) then: ### P # #(#)(P # #(#) P #(x) (#))

Citations

537	Neural networks and the bias/variance dilemma - Geman, Bienenstock, et al. - 1992
129	Beyond Grammar: An Experience-Based Theory of Language. Center for the Study of Language and Inf - Bod - 1998
119	Stochastic attribute-value grammars - Abney - 1997
16	A new probability model for data oriented parsing - Bonnema, Buying, et al. - 1999
8	Statistics: With a View Toward Applications - Breiman - 1973