AbstractThis report details experimental results of using stochastic disambiguation models for parsing sentences from the Redwoods treebank (Oepen et al., 2002). The goals of this paper are two-fold: (i) to report accuracy results on the more highly ambiguous latest version of the treebank, as compared to already published results achieved by the same stochastic models on a previous version of the corpus, and (ii) to present some newly developed models using features from the HPSG signs, as well as the MRS dependency graphs.
Similar books and articles
Feature Selection for a Rich HPSG Grammar Using Decision Trees.Christopher D. Manning & Kristina Toutanova - unknown
A Generative Constituent-Context Model for Improved Grammar Induction.Dan Klein & Christopher D. Manning - unknown
Optimizing Local Probability Models for Statistical Parsing.Mark Mitchell, Christopher D. Manning & Kristina Toutanova - unknown
A Generative Model for Semantic Role Labeling.Cynthia A. Thompson, Roger Levy & Christopher D. Manning - unknown
Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank.Dan Klein & Christopher D. Manning - unknown
Simulating many-body models in physics: Rigorous results, 'benchmarks', and cross-model justification.Axel Gelfert - unknown
The Kolmogorov-Loveland stochastic sequences are not closed under selecting subsequences.Wolfgang Merkle - 2003 - Journal of Symbolic Logic 68 (4):1362-1376.
Isomorphism and equational equivalence of continuous λ-models.Rainer Kerth - 1998 - Studia Logica 61 (3):403-415.
Added to PP
Historical graph of downloads