other,24-2-H01-1058,bq |
of the
<term>
performance
</term>
of an
<term>
|
oracle
|
</term>
. The
<term>
oracle
</term>
knows the
|
#1068
We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of anoracle. |
tech,13-6-H01-1058,bq |
behavior of the
<term>
oracle
</term>
using a
<term>
|
neural network
|
</term>
or a
<term>
decision tree
</term>
. The
|
#1165
We suggest a method that mimics the behavior of the oracle using aneural network or a decision tree. |
other,4-3-H01-1058,bq |
</term>
. The
<term>
oracle
</term>
knows the
<term>
|
reference word string
|
</term>
and selects the
<term>
word string
</term>
|
#1074
The oracle knows thereference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
other,34-3-H01-1058,bq |
<term>
word strings
</term>
, where each
<term>
|
word string
|
</term>
has been obtained by using a different
|
#1104
The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where eachword string has been obtained by using a different LM. |
other,3-4-H01-1058,bq |
different
<term>
LM
</term>
. Actually , the
<term>
|
oracle
|
</term>
acts like a
<term>
dynamic combiner
|
#1118
Actually, theoracle acts like a dynamic combiner with hard decisions using the reference. |
other,10-6-H01-1058,bq |
method that mimics the behavior of the
<term>
|
oracle
|
</term>
using a
<term>
neural network
</term>
|
#1162
We suggest a method that mimics the behavior of theoracle using a neural network or a decision tree. |
measure(ment),21-7-H01-1058,bq |
to the
<term>
LM
</term>
with the best
<term>
|
confidence
|
</term>
. We describe a three-tiered approach
|
#1193
The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the bestconfidence. |
other,1-3-H01-1058,bq |
</term>
of an
<term>
oracle
</term>
. The
<term>
|
oracle
|
</term>
knows the
<term>
reference word string
|
#1071
Theoracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |