1313 search results - page 26 / 263 » Intelligent Selection of Language Model Training Data |
120
click to vote
NAACL
2004
15 years 3 months ago
2004
We present a technique for augmenting annotated training data with hierarchical word clusters that are automatically derived from a large unannotated corpus. Cluster membership is...
137
Voted
ICTAI
2006
IEEE
15 years 8 months ago
2006
IEEE
We present an ensemble learning approach that achieves accurate predictions from arbitrarily partitioned data. The partitions come from the distributed processing requirements of ...
127
Voted
NAACL
2010
15 years 12 days ago
2010
The task of identifying the language of text or utterances has a number of applications in natural language processing. Language identification has traditionally been approached w...
131
Voted
SDM
2010
SIAM
15 years 4 months ago
2010
SIAM
We present Confidence-based Feature Acquisition (CFA), a novel supervised learning method for acquiring missing feature values when there is missing data at both training and test...
124
click to vote
ACL
2009
15 years 10 days ago
2009
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...