Sciweavers

8099 search results - page 22 / 1620
» Higher-Order Task Models
Sort
View
APAL
2010
69views more  APAL 2010»
13 years 9 months ago
Relativized Grothendieck topoi
In this paper we define a notion of relativization for higher order logic. We then show that there is a higher order theory of Grothendieck topoi such that all Grothendieck topoi ...
Nathanael Leedom Ackerman
JMLR
2010
135views more  JMLR 2010»
13 years 4 months ago
Structured Prediction Cascades
Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference i...
David Weiss, Benjamin Taskar
ICASSP
2008
IEEE
14 years 4 months ago
Language recognition with discriminative keyword selection
One commonly used approach for language recognition is to convert the input speech into a sequence of tokens such as words or phones and then to use these token sequences to deter...
Fred S. Richardson, William M. Campbell
ICML
2004
IEEE
14 years 10 months ago
Learning random walk models for inducing word dependency distributions
Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the...
Kristina Toutanova, Christopher D. Manning, Andrew...
JMLR
2012
12 years 3 days ago
Learning Low-order Models for Enforcing High-order Statistics
Models such as pairwise conditional random fields (CRFs) are extremely popular in computer vision and various other machine learning disciplines. However, they have limited expre...
Patrick Pletscher, Pushmeet Kohli