tech,9-1-C92-1055,bq |
discrimination and robustness oriented
<term>
|
adaptive learning procedure
|
</term>
is proposed to deal with the task
|
#17806
In this paper, a discrimination and robustness orientedadaptive learning procedure is proposed to deal with the task of syntactic ambiguity resolution. |
other,20-1-C92-1055,bq |
proposed to deal with the task of
<term>
|
syntactic ambiguity resolution
|
</term>
. Owing to the problem of
<term>
insufficient
|
#17817
In this paper, a discrimination and robustness oriented adaptive learning procedure is proposed to deal with the task ofsyntactic ambiguity resolution. |
other,5-2-C92-1055,bq |
resolution
</term>
. Owing to the problem of
<term>
|
insufficient training data
|
</term>
and
<term>
approximation error
</term>
|
#17826
Owing to the problem ofinsufficient training 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. |
other,9-2-C92-1055,bq |
insufficient training data
</term>
and
<term>
|
approximation error
|
</term>
introduced by the
<term>
language model
|
#17830
Owing 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. |
model,14-2-C92-1055,bq |
approximation error
</term>
introduced by the
<term>
|
language model
|
</term>
, traditional
<term>
statistical approaches
|
#17835
Owing 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. |
tech,18-2-C92-1055,bq |
language model
</term>
, traditional
<term>
|
statistical approaches
|
</term>
, which resolve
<term>
ambiguities
</term>
|
#17839
Owing 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. |
other,23-2-C92-1055,bq |
statistical approaches
</term>
, which resolve
<term>
|
ambiguities
|
</term>
by indirectly and implicitly using
|
#17844
Owing 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. |
tech,29-2-C92-1055,bq |
by indirectly and implicitly using
<term>
|
maximum likelihood method
|
</term>
, fail to achieve high
<term>
performance
|
#17850
Owing 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. |
measure(ment),37-2-C92-1055,bq |
method
</term>
, fail to achieve high
<term>
|
performance
|
</term>
in real applications . The proposed
|
#17858
Owing 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 using maximum likelihood method, fail to achieve highperformance in real applications. |
measure(ment),13-3-C92-1055,bq |
adjusting the parameters to maximize the
<term>
|
accuracy rate
|
</term>
directly . To make the proposed algorithm
|
#17876
The proposed method remedies these problems by adjusting the parameters to maximize theaccuracy rate directly. |
lr,12-4-C92-1055,bq |
the possible variations between the
<term>
|
training corpus
|
</term>
and the real tasks are also taken
|
#17892
To 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. |
other,26-4-C92-1055,bq |
into consideration by enlarging the
<term>
|
separation margin
|
</term>
between the correct candidate and
|
#17906
To 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),1-6-C92-1055,bq |
has been observed in the test . The
<term>
|
accuracy rate
|
</term>
of
<term>
syntactic disambiguation
</term>
|
#17927
Theaccuracy rate of syntactic disambiguation is raised from 46.0% to 60.62% by using this novel approach. |
tech,4-6-C92-1055,bq |
. The
<term>
accuracy rate
</term>
of
<term>
|
syntactic disambiguation
|
</term>
is raised from 46.0 % to 60.62 %
|
#17930
The accuracy rate ofsyntactic disambiguation is raised from 46.0% to 60.62% by using this novel approach. |