3716 search results - page 373 / 744 » On the monotonization of the training set |
161
click to vote
ACL
2012
13 years 9 months ago
2012
This paper presents a novel way of improving POS tagging on heterogeneous data. First, two separate models are trained (generalized and domain-specific) from the same data set by...
203
click to vote
ACL
2012
13 years 9 months ago
2012
This paper presents a novel sequence labeling model based on the latent-variable semiMarkov conditional random fields for jointly extracting argument roles of events from texts. ...
196
click to vote
SDM
2012
SIAM
13 years 9 months ago
2012
SIAM
To date, many active learning techniques have been developed for acquiring labels when training data is limited. However, an important aspect of the problem has often been neglect...
219
click to vote
AAAI
2012
13 years 9 months ago
2012
Relation extraction, the process of converting natural language text into structured knowledge, is increasingly important. Most successful techniques use supervised machine learni...
171
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...