Sciweavers

585 search results - page 7 / 117
» The Feature Subspace Method for SMT System Combination
Sort
View
ACL
2007
13 years 9 months ago
Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora
Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
Trevor Cohn, Mirella Lapata
IJON
2006
100views more  IJON 2006»
13 years 7 months ago
Analyzing the robustness of redundant population codes in sensory and feature extraction systems
Sensory systems often use groups of redundant neurons to represent stimulus information both during transduction and population coding of features. This redundancy makes the syste...
Christopher J. Rozell, Don H. Johnson
CRV
2005
IEEE
201views Robotics» more  CRV 2005»
14 years 1 months ago
Minimum Bayes Error Features for Visual Recognition by Sequential Feature Selection and Extraction
The extraction of optimal features, in a classification sense, is still quite challenging in the context of large-scale classification problems (such as visual recognition), inv...
Gustavo Carneiro, Nuno Vasconcelos
AIPS
1994
13 years 9 months ago
A Framework for Automatic Problem Decomposition in Planning
An intelligent problem solver must be able to decompose a complex problem into simpler parts. A decomposition algorithm would not only be bene cial for traditional subgoal-oriente...
Qiang Yang, Shuo Bai, Guiyou Qiu
LREC
2010
164views Education» more  LREC 2010»
13 years 9 months ago
Study of Word Sense Disambiguation System that uses Contextual Features - Approach of Combining Associative Concept Dictionary a
We propose a Word Sense Disambiguation (WSD) method that accurately classifies ambiguous words to concepts in the Associative Concept Dictionary (ACD) even when the test corpus an...
Kyota Tsutsumida, Jun Okamoto, Shun Ishizaki, Mako...