Sciweavers

1291 search results - page 127 / 259
» Learning a language model from continuous speech
Sort
View
ECTEL
2008
Springer
14 years 12 months ago
Bridging the Gap between Practitioners and E-Learning Standards: A Domain-Specific Modeling Approach
Developing a learning design using IMS Learning Design (LD) is difficult for average practitioners because a high overhead of pedagogical knowledge and technical knowledge is requi...
Yongwu Miao, Tim Sodhi, Francis Brouns, Peter B. S...
ITS
2004
Springer
129views Multimedia» more  ITS 2004»
15 years 3 months ago
Spoken Versus Typed Human and Computer Dialogue Tutoring
While human tutors typically interact with students using spoken dialogue, most computer dialogue tutors are text-based. We have conducted two experiments comparing typed and spoke...
Diane J. Litman, Carolyn Penstein Rosé, Kat...
ICML
2005
IEEE
15 years 11 months ago
Expectation maximization algorithms for conditional likelihoods
We introduce an expectation maximizationtype (EM) algorithm for maximum likelihood optimization of conditional densities. It is applicable to hidden variable models where the dist...
Jarkko Salojärvi, Kai Puolamäki, Samuel ...
CLA
2007
14 years 11 months ago
Policies Generalization in Reinforcement Learning using Galois Partitions Lattices
The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a se...
Marc Ricordeau, Michel Liquiere
COLT
1999
Springer
15 years 2 months ago
On a Generalized Notion of Mistake Bounds
This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...
Sanjay Jain, Arun Sharma