Sciweavers

694 search results - page 1 / 139
» Three new graphical models for statistical language modellin...
Sort
View
ICML
2007
IEEE
15 years 10 months ago
Three new graphical models for statistical language modelling
The supremacy of n-gram models in statistical language modelling has recently been challenged by parametric models that use distributed representations to counteract the difficult...
Andriy Mnih, Geoffrey E. Hinton
ACL
2010
14 years 7 months ago
Phrase-Based Statistical Language Generation Using Graphical Models and Active Learning
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
François Mairesse, Milica Gasic, Filip Jurc...
73
Voted
PG
2002
IEEE
15 years 2 months ago
Shape-Similarity Search of Three-Dimensional Models Using Parameterized Statistics
In this paper, we propose a method for shape-similarity search of 3D polygonal-mesh models. The system accepts triangular meshes, but tolerates degenerated polygons, disconnected ...
Ryutarou Ohbuchi, Tomo Otagiri, Masatoshi Ibato, T...
98
Voted
ACL
1997
14 years 11 months ago
Three Generative, Lexicalised Models for Statistical Parsing
In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilisti...
Michael Collins
75
Voted
CSDA
2010
118views more  CSDA 2010»
14 years 9 months ago
Grapham: Graphical models with adaptive random walk Metropolis algorithms
Recently developed adaptive Markov chain Monte Carlo (MCMC) methods have been applied successfully to many problems in Bayesian statistics. Grapham is a new open source implementat...
Matti Vihola