Sciweavers

77 search results - page 8 / 16
» Approximation Lasso Methods for Language Modeling
Sort
View
ASSETS
2007
ACM
15 years 3 months ago
Corpus studies in word prediction
Word prediction can be used to enhance the communication rate of people with disabilities who use Augmentative and Alternative Communication (AAC) devices. We use statistical meth...
Keith Trnka, Kathleen F. McCoy
WSC
2000
15 years 29 days ago
A practical approach to sample-path simulation optimization
We propose solving continuous parametric simulation optimizations using a deterministic nonlinear optimization algorithm and sample-path simulations. The optimization problem is w...
Michael C. Ferris, Todd S. Munson, Krung Sinapirom...
EMNLP
2006
15 years 1 months ago
Multilingual Deep Lexical Acquisition for HPSGs via Supertagging
We propose a conditional random fieldbased method for supertagging, and apply it to the task of learning new lexical items for HPSG-based precision grammars of English and Japanes...
Phil Blunsom, Timothy Baldwin
DCC
2010
IEEE
15 years 6 months ago
Lossless Compression Based on the Sequence Memoizer
In this work we describe a sequence compression method based on combining a Bayesian nonparametric sequence model with entropy encoding. The model, a hierarchy of Pitman-Yor proce...
Jan Gasthaus, Frank Wood, Yee Whye Teh
JMLR
2012
13 years 2 months ago
Krylov Subspace Descent for Deep Learning
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Oriol Vinyals, Daniel Povey