C00-1055 |
simple memory - based machine
|
learning techniques
|
. Since we are del ` ining a
|
A00-1040 |
more sophisticated supervised
|
learning techniques
|
for NE recognition should be
|
A00-2024 |
currently exploring using machine
|
learning techniques
|
to learn the combination rules
|
C02-1036 |
inherently complex . We use machine
|
learning techniques
|
to leverage large amounts of
|
C02-1036 |
this task by applying machine
|
learning techniques
|
. A comparison between English
|
A00-1040 |
more sophisticated supervised
|
learning techniques
|
for NE recognition should be
|
A97-1029 |
Training Data Required With any
|
learning technique
|
one of the important questions
|
A00-2005 |
boosting , two effective machine
|
learning techniques
|
, are applied to natural language
|
A00-1022 |
with statistics-based machine
|
learning techniques
|
( SML ) is called for . STP gathers
|
A00-1022 |
shallow text processing and machine
|
learning techniques
|
. It is implemented within an
|
C02-1036 |
for extraposition . As a machine
|
learning technique
|
for the problem at hand , we
|
A00-1025 |
heuristics using standard inductive
|
learning techniques
|
should help with the scalability
|
C02-1099 |
1998 ) . In the works , machine
|
learning techniques
|
such as a decision tree and a
|
C02-1085 |
documents . 3 SVMs We use a supervised
|
learning technique
|
, SVMs ( Vapnik , 1995 ) , in
|
C00-2118 |
parsed ) corpus . We apply machine
|
learning techniques
|
to determine whether the fi'equency
|
C02-1087 |
relations , our hybrid neural
|
learning technique
|
is robust to classify real-word
|
C00-2118 |
extends existing corpus-based
|
learning techniques
|
1 ; o a more complex lea.ruing
|
C00-2100 |
We present some novel nmchine
|
learning techniques
|
for the identilication of subcategorization
|
A00-2040 |
using a combination of machine
|
learning techniques
|
, as well as additional data
|
A00-1020 |
as knowledge seeds for machine
|
learning techniques
|
that operate on large amounts
|