Inducing Head-Driven PCFGs with Latent Heads: Refining a Tree-Bank Grammar for Parsing
نویسنده
چکیده
Although state-of-the-art parsers for natural language are lexicalized, it was recently shown that an accurate unlexicalized parser for the Penn tree-bank can be simply read off a manually refined tree-bank. While lexicalized parsers often suffer from sparse data, manual mark-up is costly and largely based on individual linguistic intuition. Thus, across domains, languages, and tree-bank annotations, a fundamental question arises: Is it possible to automatically induce an accurate parser from a tree-bank without resorting to full lexicalization? In this paper, we show how to induce a probabilistic parser with latent head information from simple linguistic principles. Our parser has a performance of 85.1% (LP/LR F1), which is as good as that of early lexicalized ones. This is remarkable since the induction of probabilistic grammars is in general a hard task.
منابع مشابه
Head-Driven PCFGs with Latent-Head Statistics
Although state-of-the-art parsers for natural language are lexicalized, it was recently shown that an accurate unlexicalized parser for the Penn tree-bank can be simply read off a manually refined treebank. While lexicalized parsers often suffer from sparse data, manual mark-up is costly and largely based on individual linguistic intuition. Thus, across domains, languages, and tree-bank annotat...
متن کاملTensor Decomposition for Fast Parsing with Latent-Variable PCFGs
We describe an approach to speed-up inference with latent-variable PCFGs, which have been shown to be highly effective for natural language parsing. Our approach is based on a tensor formulation recently introduced for spectral estimation of latent-variable PCFGs coupled with a tensor decomposition algorithm well-known in the multilinear algebra literature. We also describe an error bound for t...
متن کاملParsing low-resource languages using Gibbs sampling for PCFGs with latent annotations
PCFGs with latent annotations have been shown to be a very effective model for phrase structure parsing. We present a Bayesian model and algorithms based on a Gibbs sampler for parsing with a grammar with latent annotations. For PCFG-LA, we present an additional Gibbs sampler algorithm to learn annotations from training data, which are parse trees with coarse (unannotated) symbols. We show that...
متن کاملExploring the Spinal-Tig Model for Parsing French
We evaluate statistical parsing of French using two probabilistic models derived from the Tree Adjoining Grammar framework: a Stochastic Tree Insertion Grammar model (STIG) and a specific instance of this formalism, called Spinal Tree Insertion Grammar model which exhibits interesting properties with regard to data sparseness issues common to small treebanks such as the Paris 7 French Treebank....
متن کاملNon-Local Modeling with a Mixture of PCFGs
While most work on parsing with PCFGs has focused on local correlations between tree configurations, we attempt to model non-local correlations using a finite mixture of PCFGs. A mixture grammar fit with the EM algorithm shows improvement over a single PCFG, both in parsing accuracy and in test data likelihood. We argue that this improvement comes from the learning of specialized grammars that ...
متن کامل