other,16-2-J05-1003,bq |
<term>
sentence
</term>
, with associated
<term>
|
probabilities
|
</term>
that define an initial
<term>
ranking
|
#8679
The base parser produces a set of candidate parses for each input sentence, with associatedprobabilities that define an initial ranking of these parses. |
tech,43-12-J05-1003,bq |
<term>
machine translation
</term>
, or
<term>
|
natural language generation
|
</term>
. We present a novel
<term>
method
</term>
|
#8979
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 as ranking tasks, for example, speech recognition, machine translation, ornatural language generation. |
tech,4-4-J05-1003,bq |
</term>
as evidence . The strength of our
<term>
|
approach
|
</term>
is that it allows a
<term>
tree
</term>
|
#8714
The strength of ourapproach 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 these features into account. |
other,37-4-J05-1003,bq |
overlap and without the need to define a
<term>
|
derivation
|
</term>
or a
<term>
generative model
</term>
|
#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. |
tech,6-6-J05-1003,bq |
the
<term>
boosting method
</term>
to
<term>
|
parsing
|
</term>
the
<term>
Wall Street Journal treebank
|
#8792
We apply the boosting method toparsing the Wall Street Journal treebank. |
measure(ment),18-8-J05-1003,bq |
<term>
F-measure
</term>
error over the
<term>
|
baseline model ’s score
|
</term>
of 88.2 % . The article also introduces
|
#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%. |
other,45-4-J05-1003,bq |
generative model
</term>
which takes these
<term>
|
features
|
</term>
into account . We introduce a new
|
#8755
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 a derivation or a generative model which takes thesefeatures into account. |
tech,6-9-J05-1003,bq |
The article also introduces a new
<term>
|
algorithm
|
</term>
for the
<term>
boosting approach
</term>
|
#8867
The article also introduces a newalgorithm for the boosting approach which takes advantage of the sparsity of the feature space in the parsing data. |
other,4-7-J05-1003,bq |
The
<term>
method
</term>
combined the
<term>
|
log-likelihood
|
</term>
under a
<term>
baseline 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,39-12-J05-1003,bq |
,
<term>
speech recognition
</term>
,
<term>
|
machine translation
|
</term>
, or
<term>
natural language generation
|
#8975
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 as ranking tasks, for example, speech recognition,machine translation, or natural language generation. |
measure(ment),6-8-J05-1003,bq |
<term>
model
</term>
achieved 89.75 %
<term>
|
F-measure
|
</term>
, a 13 % relative decrease in
<term>
|
#8841
The new model achieved 89.75%F-measure, a 13% relative decrease in F-measure error over the baseline model’s score of 88.2%. |
other,23-9-J05-1003,bq |
of the feature space
</term>
in the
<term>
|
parsing data
|
</term>
. Experiments show significant efficiency
|
#8884
The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in theparsing data. |
tech,7-5-J05-1003,bq |
introduce a new
<term>
method
</term>
for the
<term>
|
reranking task
|
</term>
, based on the
<term>
boosting approach
|
#8766
We introduce a new method for thereranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). |
other,7-2-J05-1003,bq |
<term>
parser
</term>
produces a set of
<term>
|
candidate parses
|
</term>
for each input
<term>
sentence
</term>
|
#8670
The base parser produces a set ofcandidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. |
other,23-12-J05-1003,bq |
should be applicable to many other
<term>
|
NLP problems
|
</term>
which are naturally framed as
<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. |
tech,36-12-J05-1003,bq |
ranking tasks
</term>
, for example ,
<term>
|
speech recognition
|
</term>
,
<term>
machine translation
</term>
|
#8972
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 as ranking tasks, for example,speech recognition, machine translation, or natural language generation. |
tech,1-7-J05-1003,bq |
Street Journal treebank
</term>
. The
<term>
|
method
|
</term>
combined the
<term>
log-likelihood
</term>
|
#8800
Themethod 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 original model. |
tech,4-5-J05-1003,bq |
</term>
into account . We introduce a new
<term>
|
method
|
</term>
for the
<term>
reranking task
</term>
|
#8763
We introduce a newmethod for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). |
tech,2-8-J05-1003,bq |
original
<term>
model
</term>
. The new
<term>
|
model
|
</term>
achieved 89.75 %
<term>
F-measure
</term>
|
#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%. |
tech,8-10-J05-1003,bq |
significant efficiency gains for the new
<term>
|
algorithm
|
</term>
over the obvious
<term>
implementation
|
#8895
Experiments show significant efficiency gains for the newalgorithm over the obvious implementation of the boosting approach. |