other,26-2-P03-1005,bq |
sum
</term>
of the number of common
<term>
|
attribute sequences
|
</term>
of the
<term>
HDAGs
</term>
. We applied
|
#3833
The HDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes the weighed sum of the number of commonattribute sequences of the HDAGs. |
other,17-4-P03-1005,bq |
other
<term>
kernel functions
</term>
and
<term>
|
baseline methods
|
</term>
. Previous research has demonstrated
|
#3881
The results of the experiments demonstrate that the HDAG Kernel is superior to other kernel functions andbaseline methods. |
other,9-2-P03-1005,bq |
directly accepts several levels of both
<term>
|
chunks
|
</term>
and their
<term>
relations
</term>
,
|
#3816
The HDAG Kernel directly accepts several levels of bothchunks and their relations, and then efficiently computes the weighed sum of the number of common attribute sequences of the HDAGs. |
tech,1-2-P03-1005,bq |
natural language data
</term>
. The
<term>
|
HDAG Kernel
|
</term>
directly accepts several levels of
|
#3808
TheHDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes the weighed sum of the number of common attribute sequences of the HDAGs. |
tech,8-4-P03-1005,bq |
the experiments demonstrate that the
<term>
|
HDAG Kernel
|
</term>
is superior to other
<term>
kernel
|
#3872
The results of the experiments demonstrate that theHDAG Kernel is superior to other kernel functions and baseline methods. |
other,30-2-P03-1005,bq |
<term>
attribute sequences
</term>
of the
<term>
|
HDAGs
|
</term>
. We applied the proposed method
|
#3837
The HDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes the weighed sum of the number of common attribute sequences of theHDAGs. |
tech,4-1-P03-1005,bq |
</term>
results . This paper proposes the
<term>
|
Hierarchical Directed Acyclic Graph ( HDAG ) Kernel
|
</term>
for
<term>
structured natural language
|
#3793
This paper proposes theHierarchical Directed Acyclic Graph ( HDAG ) Kernel for structured natural language data. |
tech,22-3-P03-1005,bq |
<term>
similarity measure
</term>
and a
<term>
|
kernel function
|
</term>
. The results of the experiments
|
#3861
We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and akernel function. |
tech,14-4-P03-1005,bq |
Kernel
</term>
is superior to other
<term>
|
kernel functions
|
</term>
and
<term>
baseline methods
</term>
.
|
#3878
The results of the experiments demonstrate that the HDAG Kernel is superior to otherkernel functions and baseline methods. |
tech,6-3-P03-1005,bq |
We applied the proposed method to
<term>
|
question classification
|
</term>
and
<term>
sentence alignment tasks
|
#3845
We applied the proposed method toquestion classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function. |
other,12-2-P03-1005,bq |
of both
<term>
chunks
</term>
and their
<term>
|
relations
|
</term>
, and then efficiently computes the
|
#3819
The HDAG Kernel directly accepts several levels of both chunks and theirrelations, and then efficiently computes the weighed sum of the number of common attribute sequences of the HDAGs. |
tech,9-3-P03-1005,bq |
<term>
question classification
</term>
and
<term>
|
sentence alignment tasks
|
</term>
to evaluate its performance as a
<term>
|
#3848
We applied the proposed method to question classification andsentence alignment tasks to evaluate its performance as a similarity measure and a kernel function. |
measure(ment),18-3-P03-1005,bq |
</term>
to evaluate its performance as a
<term>
|
similarity measure
|
</term>
and a
<term>
kernel function
</term>
|
#3857
We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as asimilarity measure and a kernel function. |
other,13-1-P03-1005,bq |
Acyclic Graph ( HDAG ) Kernel
</term>
for
<term>
|
structured natural language data
|
</term>
. The
<term>
HDAG Kernel
</term>
directly
|
#3802
This paper proposes the Hierarchical Directed Acyclic Graph (HDAG) Kernel forstructured natural language data. |
other,19-2-P03-1005,bq |
and then efficiently computes the
<term>
|
weighed sum
|
</term>
of the number of common
<term>
attribute
|
#3826
The HDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes theweighed sum of the number of common attribute sequences of the HDAGs. |