file.pdf (185.57 kB)
Empirical Risk Minimization with Approximations of Probabilistic Grammars
journal contribution
posted on 2010-12-01, 00:00 authored by Shay B. Cohen, Noah A. SmithProbabilistic grammars are generative statistical models that are useful for compositional and sequential structures. We present a framework, reminiscent of structural risk minimization, for empirical risk minimization of the parameters of a fixed probabilistic grammar using the log-loss. We derive sample complexity bounds in this framework that apply both to the supervised setting and the unsupervised setting.