In this paper , a
<term>
discrimination and robustness oriented adaptive learning procedure
</term>
is proposed to deal with the task of
<term>
syntactic ambiguity resolution
</term>
.
#22773In this paper, adiscrimination and robustness oriented adaptive learning procedure is proposed to deal with the task of syntactic ambiguity resolution.
other,9-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22801Owing to the problem of insufficient training data andapproximation error introduced by the language model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications.
other,31-4-C92-1055,ak
To make the proposed
<term>
algorithm
</term>
robust , the possible variations between the
<term>
training corpus
</term>
and the real tasks are also taken into consideration by enlarging the
<term>
separation margin
</term>
between the correct
<term>
candidate
</term>
and its competing members .
#22882To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correctcandidate and its competing members.
lr,6-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22798Owing to the problem of insufficienttraining data and approximation error introduced by the language model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications.
tech,4-6-C92-1055,ak
The
<term>
accuracy rate
</term>
of
<term>
syntactic disambiguation
</term>
is raised from 46.0 % to 60.62 % by using this novel approach .
#22901The accuracy rate ofsyntactic disambiguation is raised from 46.0% to 60.62% by using this novel approach.
tech,20-1-C92-1055,ak
In this paper , a
<term>
discrimination and robustness oriented adaptive learning procedure
</term>
is proposed to deal with the task of
<term>
syntactic ambiguity resolution
</term>
.
#22788In this paper, a discrimination and robustness oriented adaptive learning procedure is proposed to deal with the task ofsyntactic ambiguity resolution.
tech,4-4-C92-1055,ak
To make the proposed
<term>
algorithm
</term>
robust , the possible variations between the
<term>
training corpus
</term>
and the real tasks are also taken into consideration by enlarging the
<term>
separation margin
</term>
between the correct
<term>
candidate
</term>
and its competing members .
#22855To make the proposedalgorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members.
other,23-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22815Owing to the problem of insufficient training data and approximation error introduced by the language model, traditional statistical approaches, which resolveambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications.
measure(ment),1-6-C92-1055,ak
The
<term>
accuracy rate
</term>
of
<term>
syntactic disambiguation
</term>
is raised from 46.0 % to 60.62 % by using this novel approach .
#22898Theaccuracy rate of syntactic disambiguation is raised from 46.0% to 60.62% by using this novel approach.
other,9-3-C92-1055,ak
The proposed method remedies these problems by adjusting the
<term>
parameters
</term>
to maximize the
<term>
accuracy rate
</term>
directly .
#22843The proposed method remedies these problems by adjusting theparameters to maximize the accuracy rate directly.
lr,12-4-C92-1055,ak
To make the proposed
<term>
algorithm
</term>
robust , the possible variations between the
<term>
training corpus
</term>
and the real tasks are also taken into consideration by enlarging the
<term>
separation margin
</term>
between the correct
<term>
candidate
</term>
and its competing members .
#22863To make the proposed algorithm robust, the possible variations between thetraining corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members.
model,14-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22806Owing to the problem of insufficient training data and approximation error introduced by thelanguage model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications.
other,26-4-C92-1055,ak
To make the proposed
<term>
algorithm
</term>
robust , the possible variations between the
<term>
training corpus
</term>
and the real tasks are also taken into consideration by enlarging the
<term>
separation margin
</term>
between the correct
<term>
candidate
</term>
and its competing members .
#22877To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging theseparation margin between the correct candidate and its competing members.
measure(ment),13-3-C92-1055,ak
The proposed method remedies these problems by adjusting the
<term>
parameters
</term>
to maximize the
<term>
accuracy rate
</term>
directly .
#22847The proposed method remedies these problems by adjusting the parameters to maximize theaccuracy rate directly.
tech,18-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22810Owing to the problem of insufficient training data and approximation error introduced by the language model, traditionalstatistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications.
tech,29-2-C92-1055,ak
Owing to the problem of insufficient
<term>
training data
</term>
and
<term>
approximation error
</term>
introduced by the
<term>
language model
</term>
, traditional
<term>
statistical approaches
</term>
, which resolve
<term>
ambiguities
</term>
by indirectly and implicitly using
<term>
maximum likelihood method
</term>
, fail to achieve high performance in real applications .
#22821Owing to the problem of insufficient training data and approximation error introduced by the language model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly usingmaximum likelihood method, fail to achieve high performance in real applications.