Sciweavers

2178 search results - page 305 / 436
» Problems of learning in multi-agent systems
Sort
View
EMNLP
2009
15 years 2 months ago
Graph Alignment for Semi-Supervised Semantic Role Labeling
Unknown lexical items present a major obstacle to the development of broadcoverage semantic role labeling systems. We address this problem with a semisupervised learning approach ...
Hagen Fürstenau, Mirella Lapata
ICASSP
2011
IEEE
14 years 8 months ago
Reconstructing completely overlapped notes from musical mixtures
In mixtures of musical sounds, the problem of overlapped harmonics poses a significant challenge to source separation. Common Amplitude Modulation (CAM) is one of the most effect...
Jinyu Han, Bryan Pardo
EDBT
1994
ACM
117views Database» more  EDBT 1994»
15 years 8 months ago
Content Routing for Distributed Information Servers
We describe a system that provides query based associative access to the contents of distributed information servers. In typical distributed information systems there are so many o...
Mark A. Sheldon, Andrzej Duda, Ron Weiss, James O'...
ICCBR
2001
Springer
15 years 9 months ago
Meta-case-Based Reasoning: Using Functional Models to Adapt Case-Based Agents
It is useful for an intelligent software agent to be able to adapt to new demands from an environment. Such adaptation can be viewed as a redesign problem; an agent has some origin...
J. William Murdock, Ashok K. Goel
ICML
2008
IEEE
16 years 5 months ago
Exploration scavenging
We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
John Langford, Alexander L. Strehl, Jennifer Wortm...