Sciweavers

342 search results - page 15 / 69
» Refining Generative Language Models using Discriminative Lea...
Sort
View
ACL
2006
13 years 8 months ago
Learning to Say It Well: Reranking Realizations by Predicted Synthesis Quality
This paper presents a method for adapting a language generator to the strengths and weaknesses of a synthetic voice, thereby improving the naturalness of synthetic speech in a spo...
Crystal Nakatsu, Michael White
ICRA
2008
IEEE
170views Robotics» more  ICRA 2008»
14 years 1 months ago
Modeling and recognition of actions through motor primitives
— We investigate modeling and recognition of object manipulation actions for the purpose of imitation based learning in robotics. To model the process, we are using a combination...
David Martínez Mercado, Danica Kragic
UCS
2007
Springer
14 years 1 months ago
Discriminative Temporal Smoothing for Activity Recognition from Wearable Sensors
Abstract. This paper describes daily life activity recognition using wearable acceleration sensors attached to four different parts of the human body. The experimental data set con...
Jaakko Suutala, Susanna Pirttikangas, Juha Rö...
INLG
2010
Springer
13 years 5 months ago
Named Entity Generation Using Sampling-based Structured Prediction
The problem of Named Entity Generation is expressed as a conditional probability model over a structured domain. By defining a factor-graph model over the mentions of a text, we o...
Guillaume Bouchard
ICML
2008
IEEE
14 years 8 months ago
Extracting and composing robust features with denoising autoencoders
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...