Sciweavers

268 search results - page 44 / 54
» Improving IBM Word Alignment Model 1
Sort
View
CVPR
2007
IEEE
16 years 1 months ago
Learning Visual Representations using Images with Captions
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
Ariadna Quattoni, Michael Collins, Trevor Darrell
PKDD
2010
Springer
168views Data Mining» more  PKDD 2010»
14 years 10 months ago
Bayesian Knowledge Corroboration with Logical Rules and User Feedback
Current knowledge bases suffer from either low coverage or low accuracy. The underlying hypothesis of this work is that user feedback can greatly improve the quality of automatica...
Gjergji Kasneci, Jurgen Van Gael, Ralf Herbrich, T...
EMNLP
2010
14 years 9 months ago
Simple Type-Level Unsupervised POS Tagging
Part-of-speech (POS) tag distributions are known to exhibit sparsity -- a word is likely to take a single predominant tag in a corpus. Recent research has demonstrated that incorp...
Yoong Keok Lee, Aria Haghighi, Regina Barzilay
HICSS
2002
IEEE
113views Biometrics» more  HICSS 2002»
15 years 4 months ago
Persona: A Contextualized and Personalized Web Search
Abstract— Recent advances in graph-based search techniques derived from Kleinberg’s work [1] have been impressive. This paper further improves the graph-based search algorithm ...
Francisco Tanudjaja, Lik Mu
DCC
2002
IEEE
15 years 11 months ago
Optimized Edgebreaker Encoding for Large and Regular Triangle Meshes
We present a technique designed aiming to improve the compression of the Edgebreaker CLERS string for large and regular meshes, where regularity is understood as the compactness o...
Andrzej Szymczak