W06-1623 |
Segmentation Our approach for
|
temporal segmentation
|
requires annotated data for supervised
|
W06-1623 |
Evaluation Measures We evaluate
|
temporal segmentation
|
by considering the ratio of correctly
|
W06-1623 |
hypothesis about the reliability of
|
temporal segmentation
|
. Once we established high inter-annotator
|
W06-1623 |
segmentation . 7 Results We evaluate
|
temporal segmentation
|
using leaveone-out cross-validation
|
W06-1623 |
boundary . Topical Continuity
|
Temporal segmentation
|
is closely related to topical
|
W06-1623 |
other diseases ) . 6.2 Annotating
|
Temporal Segmentation
|
Our approach for temporal segmentation
|
W06-1623 |
such transitions is relevant for
|
temporal segmentation
|
. We quantify the strength of
|
W06-1623 |
et al. , 2003 ) . 4 Method for
|
Temporal Segmentation
|
Our first goal is to automatically
|
W06-1623 |
method achieves 83 % F-measure in
|
temporal segmentation
|
and 84 % accuracy in inferring
|
W06-1623 |
learn them from data . We model
|
temporal segmentation
|
as a binary classification task
|
W11-4208 |
research tasks related to its
|
temporal segmentation
|
. 3.2 Methods We have developed
|
E12-2016 |
integration within a framework for
|
temporal segmentation
|
of the Patient history into episodes
|
W11-4200 |
´ el ` ene Metzger Towards
|
Temporal Segmentation
|
of Patient History in Discharge
|