Author： Toutanova Kristina Manning Christopher Flickinger Dan Oepen Stephan
Publisher： Springer Publishing Company
ISSN： 1570-7075
Source： Research on Language and Computation, Vol.3, Iss.1, 2005-04, pp. : 83-105
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
This article details our experiments on HPSG parse disambiguation, based on the Redwoods treebank. Using existing and novel stochastic models, we evaluate the usefulness of different information sources for disambiguation – lexical, syntactic, and semantic. We perform careful comparisons of generative and discriminative models using equivalent features and show the consistent advantage of discriminatively trained models. Our best system performs at over 76% sentence exact match accuracy.
Related content
Access to resources
Recommend
Disambiguation preferences and corpus frequencies in noun phrase conjunction
Journal of Memory and Language, Vol. 49, Iss. 3, 2003-10 ,pp. :