A00-1022 |
ICC-MAIL database for use in future
|
learning
|
steps . Other features of the
|
A00-1022 |
to the document categories The
|
learning
|
phase defines thresholds for
|
A00-1020 |
. To be able to develop such a
|
learning
|
approach , we must first develop
|
A00-1022 |
preprocessing used . During the
|
learning
|
phase , each document is pre
|
A00-1002 |
see Haji , Hladka ( 1998 ) . The
|
learning
|
is based on a manually tagged
|
A00-1022 |
accuracy after repeating the off-line
|
learning
|
step . If a new category is introduced
|
A00-1022 |
different linguistic preprocessing and
|
learning
|
algorithms and provide some interpretations
|
A00-1022 |
documents as vectors during the
|
learning
|
phase . In the categorization
|
A00-1022 |
with statistics-based machine
|
learning
|
techniques ( SML ) is called
|
A00-1022 |
application , we tried out the
|
Learning
|
Vector Quantization ( LVQ ) (
|
A00-1022 |
shallow text processing and machine
|
learning
|
techniques . It is implemented
|
A00-1022 |
to a certain class during the
|
learning
|
phase , e.g. decision trees ,
|
A00-1022 |
kind of " non-symbolic " eager
|
learning
|
algo - 1 60 rithm . The neural
|
A00-1022 |
Sommerfield , 1996 ) . Symbolic Eager
|
Learning
|
: This type of learners constructs
|
A00-1012 |
of extra features to a machine
|
learning
|
algorithm then it is possible
|
A00-1022 |
construct a representation during the
|
learning
|
phase , namely a hyper plane
|
A00-1022 |
workflow of the system consists of a
|
learning
|
step carried out off-line ( the
|
A00-1022 |
kind of preprocessing and which
|
learning
|
algorithm is most appropriate
|
A00-1020 |
as knowledge seeds for machine
|
learning
|
techniques that operate on large
|
A00-1020 |
as an ideal framework for text
|
learning
|
tasks that have knowledge seeds
|