1313 search results - page 21 / 263 » Intelligent Selection of Language Model Training Data |
158
Voted
EMNLP
2010
15 years 15 days ago
2010
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...
ICASSP
2011
IEEE
14 years 6 months ago
2011
IEEE
Cross-lingual voice transformation is challenging when source language (L1) and target language (L2) are very different in corresponding phonetics and prosodies. We propose a fram...
105
click to vote
NAACL
2003
15 years 3 months ago
2003
This paper describes an application of active learning methods to the classification of phone strings recognized using unsupervised phonotactic models. The only training data req...
134
click to vote
GECCO
2008
Springer
15 years 3 months ago
2008
Springer
Selective sampling is a form of active learning which can reduce the cost of training by only drawing informative data points into the training set. This selected training set is ...
172
click to vote
ICDAR
2009
IEEE
15 years 7 days ago
2009
IEEE
In our previous work, a precision constrained Gaussian model (PCGM) was proposed for character modeling to design compact recognizers of handwritten Chinese characters. A maximum ...