Sciweavers

4078 search results - page 556 / 816
» Automatic rate adaptation
Sort
View
COLING
2002
15 years 7 months ago
Recovering Latent Information in Treebanks
Many recent statistical parsers rely on a preprocessing step which uses hand-written, corpus-specific rules to augment the training data with extra information. For example, head-...
David Chiang, Daniel M. Bikel
DEBU
2000
95views more  DEBU 2000»
15 years 7 months ago
Accurately and Reliably Extracting Data from the Web: A Machine Learning Approach
A critical problem in developing information agents for the Web is accessing data that is formatted for human use. We have developed a set of tools for extracting data from web si...
Craig A. Knoblock, Kristina Lerman, Steven Minton,...
PAMI
1998
85views more  PAMI 1998»
15 years 6 months ago
Shape Evolution With Structural and Topological Changes Using Blending
This paper describes a framework for the estimation of shape from sparse or incomplete range data. It uses a shape representation called blending, which allows for the geometric c...
Douglas DeCarlo, Dimitris N. Metaxas
PR
2002
129views more  PR 2002»
15 years 6 months ago
Text extraction in complex color documents
Text extraction in mixed-type documents is a pre-processing and necessary stage for many document applications. In mixed-type color documents, text, drawings and graphics appear w...
Charalambos Strouthopoulos, Nikos Papamarkos, Anto...
SPEECH
1998
118views more  SPEECH 1998»
15 years 6 months ago
Dimensionality reduction of electropalatographic data using latent variable models
We consider the problem of obtaining a reduced dimension representation of electropalatographic (EPG) data. An unsupervised learning approach based on latent variable modelling is...
Miguel Á. Carreira-Perpiñán, ...