Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the approach 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>
.
#8340Although 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 as ranking tasks, for example, speech recognition,machine translation, or natural language generation.
other,21-2-J05-1003,ak
The
<term>
base parser
</term>
produces a set of
<term>
candidate parses
</term>
for each
<term>
input sentence
</term>
, with associated
<term>
probabilities
</term>
that define an initial
<term>
ranking
</term>
of these
<term>
parses
</term>
.
#8049The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initialranking of these parses.
other,23-9-J05-1003,ak
The article also introduces a new
<term>
algorithm
</term>
for the
<term>
boosting approach
</term>
which takes advantage of the
<term>
sparsity
</term>
of the
<term>
feature space
</term>
in the
<term>
parsing data
</term>
.
#8249The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in theparsing data.
tech,15-10-J05-1003,ak
Experiments show significant efficiency gains for the new
<term>
algorithm
</term>
over the obvious implementation of the
<term>
boosting approach
</term>
.
#8267Experiments show significant efficiency gains for the new algorithm over the obvious implementation of theboosting approach.
other,26-4-J05-1003,ak
The strength of our approach 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 .
#8101The 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.
other,16-2-J05-1003,ak
The
<term>
base parser
</term>
produces a set of
<term>
candidate parses
</term>
for each
<term>
input sentence
</term>
, with associated
<term>
probabilities
</term>
that define an initial
<term>
ranking
</term>
of these
<term>
parses
</term>
.
#8044The base parser produces a set of candidate parses for each input sentence, with associatedprobabilities that define an initial ranking of these parses.
other,4-7-J05-1003,ak
The method combined the
<term>
log-likelihood under a baseline model
</term>
( that of Collins [ 1999 ] ) 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>
.
#8168The 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.
other,25-7-J05-1003,ak
The method combined the
<term>
log-likelihood under a baseline model
</term>
( that of Collins [ 1999 ] ) 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>
.
#8189The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features overparse trees that were not included in the original model.
other,16-9-J05-1003,ak
The article also introduces a new
<term>
algorithm
</term>
for the
<term>
boosting approach
</term>
which takes advantage of the
<term>
sparsity
</term>
of the
<term>
feature space
</term>
in the
<term>
parsing data
</term>
.
#8242The article also introduces a new algorithm for the boosting approach which takes advantage of thesparsity of the feature space in the parsing data.
measure(ment),14-8-J05-1003,ak
The new
<term>
model
</term>
achieved 89.75 %
<term>
F-measure
</term>
, a 13 % relative decrease in
<term>
F-measure error
</term>
over the
<term>
baseline model ’s
</term>
score of 88.2 % .
#8214The new model achieved 89.75% F-measure, a 13% relative decrease inF-measure error over the baseline model’s score of 88.2%.
tech,1-2-J05-1003,ak
The
<term>
base parser
</term>
produces a set of
<term>
candidate parses
</term>
for each
<term>
input sentence
</term>
, with associated
<term>
probabilities
</term>
that define an initial
<term>
ranking
</term>
of these
<term>
parses
</term>
.
#8029Thebase parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses.
tech,3-6-J05-1003,ak
We apply the
<term>
boosting method
</term>
to parsing the
<term>
Wall Street Journal treebank
</term>
.
#8154We apply theboosting method to parsing the Wall Street Journal treebank.
other,17-3-J05-1003,ak
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 .
#8071A second model then attempts to improve upon this initial ranking, using additional features of thetree as evidence.
other,30-12-J05-1003,ak
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the approach 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>
.
#8331Although 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.
measure(ment),6-8-J05-1003,ak
The new
<term>
model
</term>
achieved 89.75 %
<term>
F-measure
</term>
, a 13 % relative decrease in
<term>
F-measure error
</term>
over the
<term>
baseline model ’s
</term>
score of 88.2 % .
#8206The new model achieved 89.75%F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%.
tech,9-9-J05-1003,ak
The article also introduces a new
<term>
algorithm
</term>
for the
<term>
boosting approach
</term>
which takes advantage of the
<term>
sparsity
</term>
of the
<term>
feature space
</term>
in the
<term>
parsing data
</term>
.
#8235The article also introduces a new algorithm for theboosting approach which takes advantage of the sparsity of the feature space in the parsing data.
other,45-4-J05-1003,ak
The strength of our approach 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 .
#8120The 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 a derivation or a generative model which takes thesefeatures into account.
model,2-8-J05-1003,ak
The new
<term>
model
</term>
achieved 89.75 %
<term>
F-measure
</term>
, a 13 % relative decrease in
<term>
F-measure error
</term>
over the
<term>
baseline model ’s
</term>
score of 88.2 % .
#8202The newmodel achieved 89.75% F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%.
tech,8-10-J05-1003,ak
Experiments show significant efficiency gains for the new
<term>
algorithm
</term>
over the obvious implementation of the
<term>
boosting approach
</term>
.
#8260Experiments show significant efficiency gains for the newalgorithm over the obvious implementation of the boosting approach.
tech,23-12-J05-1003,ak
Although the experiments in this article are on
<term>
natural language parsing ( NLP )
</term>
, the approach 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>
.
#8324Although 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.