118 search results - page 15 / 24 » Unlabeled data improves word prediction |
119
Voted
COLING
2008
15 years 3 months ago
2008
It is difficult to identify sentence importance from a single point of view. In this paper, we propose a learning-based approach to combine various sentence features. They are cat...
140
click to vote
WWW
2009
ACM
16 years 2 months ago
2009
ACM
Transferring knowledge from one domain to another is challenging due to a number of reasons. Since both conditional and marginal distribution of the training data and test data ar...
114
click to vote
KDD
2004
ACM
16 years 2 months ago
2004
ACM
We use clustering to derive new relations which augment database schema used in automatic generation of predictive features in statistical relational learning. Clustering improves...
120
click to vote
CVPR
2008
IEEE
16 years 3 months ago
2008
IEEE
Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism ? animal ? feline ? cat). What about defining a hierarchy based on the visual ...
259
click to vote
WWW
2011
ACM
14 years 8 months ago
2011
ACM
The explosion of Web opinion data has made essential the need for automatic tools to analyze and understand people’s sentiments toward different topics. In most sentiment analy...