Sciweavers

16218 search results - page 193 / 3244
» Standards
Sort
View
MT
2006
101views more  MT 2006»
15 years 4 months ago
EBMT by tree-phrasing
We present a study we conducted to build a repository storing associations between simple dependency treelets in a source language and their corresponding phrases in a target lang...
Philippe Langlais, Fabrizio Gotti
107
Voted
PAMI
2006
164views more  PAMI 2006»
15 years 4 months ago
Adaptive Support-Weight Approach for Correspondence Search
We present a new window-based method for correspondence search using varying support-weights. We adjust the support-weights of the pixels in a given support window based on color s...
Kuk-Jin Yoon, In-So Kweon
138
Voted
SIGIR
2008
ACM
15 years 4 months ago
Relevance assessment: are judges exchangeable and does it matter
We investigate to what extent people making relevance judgements for a reusable IR test collection are exchangeable. We consider three classes of judge: "gold standard" ...
Peter Bailey, Nick Craswell, Ian Soboroff, Paul Th...
TIT
2008
76views more  TIT 2008»
15 years 4 months ago
Improved Risk Tail Bounds for On-Line Algorithms
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
Nicolò Cesa-Bianchi, Claudio Gentile
123
Voted
BSL
2005
74views more  BSL 2005»
15 years 4 months ago
Turing computations on ordinals
We define the notion of ordinal computability by generalizing standard Turing computability on tapes of length to computations on tapes of arbitrary ordinal length. We show that a ...
Peter Koepke