Sciweavers

5128 search results - page 196 / 1026
» When Abstraction Fails
Sort
View
NAACL
2004
15 years 8 months ago
The Web as a Baseline: Evaluating the Performance of Unsupervised Web-based Models for a Range of NLP Tasks
Previous work demonstrated that web counts can be used to approximate bigram frequencies, and thus should be useful for a wide variety of NLP tasks. So far, only two generation ta...
Mirella Lapata, Frank Keller
NIPS
2001
15 years 8 months ago
Model Based Population Tracking and Automatic Detection of Distribution Changes
Probabilistic mixture models are used for a broad range of data analysis tasks such as clustering, classification, predictive modeling, etc. Due to their inherent probabilistic na...
Igor V. Cadez, Paul S. Bradley
SFP
2001
15 years 8 months ago
Function Types in Complete Type Inference
: We study type checking that is complete in the sense that it accepts every program whose subexpressions can all be executed without raising a type error at runtime. In a complete...
Manfred Widera, Christoph Beierle
IJCAI
2003
15 years 8 months ago
Approximating Optimal Policies for Agents with Limited Execution Resources
An agent with limited consumable execution resources needs policies that attempt to achieve good performance while respecting these limitations. Otherwise, an agent (such as a pla...
Dmitri A. Dolgov, Edmund H. Durfee
IM
2003
15 years 8 months ago
Hierarchical End-to-End Service Recovery
: Failed networks, for example MPLS, can cause signaling storms the size of which can grow dramatically with network size. This paper presents a new scalable fault notification pro...
Mohamed El-Darieby, Dorina C. Petriu, Jerry Rolia