1313 search results - page 19 / 263 » Intelligent Selection of Language Model Training Data |
105
click to vote
INFORMATICALT
2007
15 years 2 months ago
2007
In this article we present the general architecture of a hybrid neuro-symbolic system for the selection and stepwise elimination of predictor variables and non-relevant individuals...
136
click to vote
BIS
2007
15 years 3 months ago
2007
Business intelligence requires the collecting and merging of information from many different sources, both structured and unstructured, in order to analyse for example financial ...
118
click to vote
EMNLP
2004
15 years 3 months ago
2004
Active learning (AL) promises to reduce the cost of annotating labeled datasets for trainable human language technologies. Contrary to expectations, when creating labeled training...
115
click to vote
ACL
2012
13 years 4 months ago
2012
We present a novel algorithm for multilingual dependency parsing that uses annotations from a diverse set of source languages to parse a new unannotated language. Our motivation i...
140
Voted
JMLR
2010
14 years 9 months ago
2010
We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...