Sciweavers

2747 search results - page 254 / 550
» Non-oblivious Strategy Improvement
Sort
View
ACL
2010
14 years 10 months ago
Minimized Models and Grammar-Informed Initialization for Supertagging with Highly Ambiguous Lexicons
We combine two complementary ideas for learning supertaggers from highly ambiguous lexicons: grammar-informed tag transitions and models minimized via integer programming. Each st...
Sujith Ravi, Jason Baldridge, Kevin Knight
ML
2011
ACM
308views Machine Learning» more  ML 2011»
14 years 6 months ago
Relational information gain
Abstract. Type Extension Trees (TET) have been recently introduced as an expressive representation language allowing to encode complex combinatorial features of relational entities...
Marco Lippi, Manfred Jaeger, Paolo Frasconi, Andre...
ASPLOS
2011
ACM
14 years 3 months ago
RCDC: a relaxed consistency deterministic computer
Providing deterministic execution significantly simplifies the debugging, testing, replication, and deployment of multithreaded programs. Recent work has developed deterministic...
Joseph Devietti, Jacob Nelson, Tom Bergan, Luis Ce...
CVPR
2009
IEEE
16 years 7 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
ICCV
2007
IEEE
16 years 1 months ago
A 3D Teacher for Car Detection in Aerial Images
This paper demonstrates how to reduce the hand labeling effort considerably by 3D information in an object detection task. In particular, we demonstrate how an efficient car detec...
Stefan Kluckner, Georg Pacher, Helmut Grabner, Hor...