P06-2031 |
el , ef ) : Chinese to English
|
word sense translation
|
probability . ( 1 ) Word senses
|
P06-2031 |
entries in FrameNet . An example of
|
word sense translation
|
from our algorithm output is
|
P06-2031 |
Word Sense Translation Previous
|
word sense translation
|
methods are based on using context
|
P06-2031 |
shown in Table 1 be - low . The
|
word sense translation
|
accuracies of the above words
|
P06-2031 |
English FrameNet , the average
|
word sense translation
|
accuracy is 82 % . Applying the
|
P06-2031 |
have improved the accuracy of
|
word sense translation
|
using the current method . Table
|
P06-2031 |
erro - neous . The accuracy of
|
word sense translations
|
on this evaluation set of example
|
P06-2031 |
translation corresponds to the
|
word sense translation
|
we described in the previous
|
P06-2031 |
Communications Foundation . <title> Robust
|
Word Sense Translation
|
by EM Learning of Frame Semantics
|
P06-2031 |
are not correctly mapped , then
|
word sense translation
|
accuracy suffers . The main advantage
|
P06-2031 |
Table 3 . Our method improves
|
word sense translation
|
precision over Fung and Chen
|
P06-2031 |
Figure 6 , there are altogether 147
|
word sense translations
|
for ( hold , detaining ) . We
|
P06-2031 |
Semantics We evaluate the accuracy of
|
word sense translation
|
in our automatically generated
|
P06-2031 |
, human | 人 . 4 Robust
|
Word Sense Translation
|
Using Frame Semantics We evaluate
|
P11-2055 |
scores ) are then stored in a
|
word sense translation
|
table , in which look-ups are
|
S10-1026 |
process results in an English
|
word sense translation
|
table ( WSTT ) . The word senses
|
E14-4011 |
approach to accurately detecting
|
word sense translation
|
errors ( WSTEs ) of ambiguous
|
P06-2031 |
translation likelihoods , our
|
word sense translation
|
accuracies are very high , at
|
P06-2031 |
cluster Chinese verb senses .
|
Word Sense Translation
|
Previous word sense translation
|
P06-2031 |
detaining ) . We then find the
|
word sense translation
|
with the highest probability
|