Empirical Risk Minimization with Approximations of Probabilistic Grammars
Shay B. Cohen
Noah A. Smith
10.1184/R1/6473354.v1
https://kilthub.cmu.edu/articles/journal_contribution/Empirical_Risk_Minimization_with_Approximations_of_Probabilistic_Grammars/6473354
<p>Probabilistic 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.</p>
2010-12-01 00:00:00
Language Technologies