Sciweavers

6 search results - page 1 / 2
» A Structured Language Model Based on Context-Sensitive Proba...
Sort
View
IBPRIA
2003
Springer
13 years 10 months ago
Smoothing Techniques for Tree-k-Grammar-Based Natural Language Modeling
Abstract. In a previous work, a new probabilistic context-free grammar (PCFG) model for natural language parsing derived from a tree bank corpus has been introduced. The model esti...
Jose L. Verdú-Mas, Jorge Calera-Rubio, Rafa...
ACL
1993
13 years 6 months ago
Towards History-Based Grammars: Using Richer Models for Probabilistic Parsing
We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates...
Ezra Black, Frederick Jelinek, John D. Lafferty, D...
NIPS
2001
13 years 6 months ago
Natural Language Grammar Induction Using a Constituent-Context Model
This paper presents a novel approach to the unsupervised learning of syntactic analyses of natural language text. Most previous work has focused on maximizing likelihood according...
Dan Klein, Christopher D. Manning
EMNLP
2007
13 years 6 months ago
Fast and Robust Multilingual Dependency Parsing with a Generative Latent Variable Model
We use a generative history-based model to predict the most likely derivation of a dependency parse. Our probabilistic model is based on Incremental Sigmoid Belief Networks, a rec...
Ivan Titov, James Henderson