model,34-7-J05-1003,bq |
The
<term>
method
</term>
combined the
<term>
log-likelihood
</term>
under a
<term>
baseline model
</term>
( that of
<term>
Collins [ 1999 ]
</term>
) with evidence from an additional 500,000
<term>
features
</term>
over
<term>
parse trees
</term>
that were not included in the original
<term>
model
</term>
.
|
#8833
The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the originalmodel. |
tech,8-12-J05-1003,bq |
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the
<term>
approach
</term>
should be applicable to many other
<term>
NLP problems
</term>
which are naturally framed as
<term>
ranking tasks
</term>
, for example ,
<term>
speech recognition
</term>
,
<term>
machine translation
</term>
, or
<term>
natural language generation
</term>
.
|
#8944
Although the experiments in this article are onnatural language parsing ( NLP ), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. |
other,14-3-J05-1003,bq |
A second
<term>
model
</term>
then attempts to improve upon this initial
<term>
ranking
</term>
, using additional
<term>
features
</term>
of the
<term>
tree
</term>
as evidence .
|
#8703
A second model then attempts to improve upon this initial ranking, using additionalfeatures of the tree as evidence. |
other,17-3-J05-1003,bq |
A second
<term>
model
</term>
then attempts to improve upon this initial
<term>
ranking
</term>
, using additional
<term>
features
</term>
of the
<term>
tree
</term>
as evidence .
|
#8706
A second model then attempts to improve upon this initial ranking, using additional features of thetree as evidence. |
other,26-4-J05-1003,bq |
The strength of our
<term>
approach
</term>
is that it allows a
<term>
tree
</term>
to be represented as an arbitrary set of
<term>
features
</term>
, without concerns about how these
<term>
features
</term>
interact or overlap and without the need to define a
<term>
derivation
</term>
or a
<term>
generative model
</term>
which takes these
<term>
features
</term>
into account .
|
#8736
The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how thesefeatures interact or overlap and without the need to define a derivation or a generative model which takes these features into account. |
tech,2-3-J05-1003,bq |
A second
<term>
model
</term>
then attempts to improve upon this initial
<term>
ranking
</term>
, using additional
<term>
features
</term>
of the
<term>
tree
</term>
as evidence .
|
#8691
A secondmodel then attempts to improve upon this initial ranking, using additional features of the tree as evidence. |
other,20-5-J05-1003,bq |
We introduce a new
<term>
method
</term>
for the
<term>
reranking task
</term>
, based on the
<term>
boosting approach
</term>
to
<term>
ranking problems
</term>
described in
<term>
Freund et al. ( 1998 )
</term>
.
|
#8779
We introduce a new method for the reranking task, based on the boosting approach to ranking problems described inFreund et al. ( 1998 ). |
tech,2-8-J05-1003,bq |
The new
<term>
model
</term>
achieved 89.75 %
<term>
F-measure
</term>
, a 13 % relative decrease in
<term>
F-measure
</term>
error over the
<term>
baseline model ’s score
</term>
of 88.2 % .
|
#8837
The newmodel achieved 89.75% F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%. |
other,4-7-J05-1003,bq |
The
<term>
method
</term>
combined the
<term>
log-likelihood
</term>
under a
<term>
baseline model
</term>
( that of
<term>
Collins [ 1999 ]
</term>
) with evidence from an additional 500,000
<term>
features
</term>
over
<term>
parse trees
</term>
that were not included in the original
<term>
model
</term>
.
|
#8803
The method combined thelog-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. |
tech,8-10-J05-1003,bq |
Experiments show significant efficiency gains for the new
<term>
algorithm
</term>
over the obvious
<term>
implementation
</term>
of the
<term>
boosting approach
</term>
.
|
#8895
Experiments show significant efficiency gains for the newalgorithm over the obvious implementation of the boosting approach. |
tech,16-12-J05-1003,bq |
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the
<term>
approach
</term>
should be applicable to many other
<term>
NLP problems
</term>
which are naturally framed as
<term>
ranking tasks
</term>
, for example ,
<term>
speech recognition
</term>
,
<term>
machine translation
</term>
, or
<term>
natural language generation
</term>
.
|
#8952
Although the experiments in this article are on natural language parsing (NLP), theapproach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. |
tech,3-6-J05-1003,bq |
We apply the
<term>
boosting method
</term>
to
<term>
parsing
</term>
the
<term>
Wall Street Journal treebank
</term>
.
|
#8789
We apply theboosting method to parsing the Wall Street Journal treebank. |
other,23-12-J05-1003,bq |
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the
<term>
approach
</term>
should be applicable to many other
<term>
NLP problems
</term>
which are naturally framed as
<term>
ranking tasks
</term>
, for example ,
<term>
speech recognition
</term>
,
<term>
machine translation
</term>
, or
<term>
natural language generation
</term>
.
|
#8959
Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many otherNLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation. |
measure(ment),18-8-J05-1003,bq |
The new
<term>
model
</term>
achieved 89.75 %
<term>
F-measure
</term>
, a 13 % relative decrease in
<term>
F-measure
</term>
error over the
<term>
baseline model ’s score
</term>
of 88.2 % .
|
#8853
The new model achieved 89.75% F-measure, a 13% relative decrease in F-measure error over thebaseline model ’s score of 88.2%. |
tech,6-6-J05-1003,bq |
We apply the
<term>
boosting method
</term>
to
<term>
parsing
</term>
the
<term>
Wall Street Journal treebank
</term>
.
|
#8792
We apply the boosting method toparsing the Wall Street Journal treebank. |
tech,7-5-J05-1003,bq |
We introduce a new
<term>
method
</term>
for the
<term>
reranking task
</term>
, based on the
<term>
boosting approach
</term>
to
<term>
ranking problems
</term>
described in
<term>
Freund et al. ( 1998 )
</term>
.
|
#8766
We introduce a new method for thereranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). |
other,37-4-J05-1003,bq |
The strength of our
<term>
approach
</term>
is that it allows a
<term>
tree
</term>
to be represented as an arbitrary set of
<term>
features
</term>
, without concerns about how these
<term>
features
</term>
interact or overlap and without the need to define a
<term>
derivation
</term>
or a
<term>
generative model
</term>
which takes these
<term>
features
</term>
into account .
|
#8747
The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define aderivation or a generative model which takes these features into account. |
other,21-2-J05-1003,bq |
The base
<term>
parser
</term>
produces a set of
<term>
candidate parses
</term>
for each input
<term>
sentence
</term>
, with associated
<term>
probabilities
</term>
that define an initial
<term>
ranking
</term>
of these
<term>
parses
</term>
.
|
#8684
The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initialranking of these parses. |
tech,15-10-J05-1003,bq |
Experiments show significant efficiency gains for the new
<term>
algorithm
</term>
over the obvious
<term>
implementation
</term>
of the
<term>
boosting approach
</term>
.
|
#8902
Experiments show significant efficiency gains for the new algorithm over the obvious implementation of theboosting approach. |
tech,30-12-J05-1003,bq |
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the
<term>
approach
</term>
should be applicable to many other
<term>
NLP problems
</term>
which are naturally framed as
<term>
ranking tasks
</term>
, for example ,
<term>
speech recognition
</term>
,
<term>
machine translation
</term>
, or
<term>
natural language generation
</term>
.
|
#8966
Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed asranking tasks, for example, speech recognition, machine translation, or natural language generation. |