Sciweavers

438 search results - page 39 / 88
» Shallow Dependency Labeling
Sort
View
ALT
2006
Springer
14 years 5 months ago
Active Learning in the Non-realizable Case
Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly c...
Matti Kääriäinen
ICML
2008
IEEE
14 years 9 months ago
Semi-supervised learning of compact document representations with deep networks
Finding good representations of text documents is crucial in information retrieval and classification systems. Today the most popular document representation is based on a vector ...
Marc'Aurelio Ranzato, Martin Szummer
SETN
2010
Springer
14 years 3 months ago
A Feasibility Study on Low Level Techniques for Improving Parsing Accuracy for Spanish Using Maltparser
In the last years dependency parsing has been accomplished by machine learning–based systems showing great accuracy but usually under 90% for Labelled Attachment Score (LAS). Mal...
Miguel Ballesteros, Jesús Herrera, Virginia...
VTC
2007
IEEE
142views Communications» more  VTC 2007»
14 years 3 months ago
Iterative Demodulation and Decoding for Rotated MPSK Constellations with Convolutional Coding and Signal Space Diversity
— Signal space diversity (SSD) with the rotation of the signal constellation using multi-level modulation schemes is known to provide good performance gains over fading channels....
Nauman F. Kiyani, Jos H. Weber
COLT
2005
Springer
14 years 2 months ago
The Value of Agreement, a New Boosting Algorithm
We present a new generalization bound where the use of unlabeled examples results in a better ratio between training-set size and the resulting classifier’s quality and thus red...
Boaz Leskes