tech,4-1-H05-1095,bq |
phrase-based statistical machine translation
|
method
|
</term>
, based on
<term>
non-contiguous phrases
|
#7345
This paper presents a phrase-based statistical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps. |
tech,29-2-C92-1055,bq |
implicitly using
<term>
maximum likelihood
|
method
|
</term>
, fail to achieve high
<term>
performance
|
#17852
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 high performance in real applications. |
|
<term>
manual transcription
</term>
. In our
|
method
|
,
<term>
unsupervised training
</term>
is first
|
#2257
In our method, unsupervised training is first used to train a phone n-gram model for a particular domain; the output of recognition with this model is then passed to a phone-string classifier. |
tech,2-3-P05-3025,bq |
systems
</term>
. Using this
<term>
visualization
|
method
|
</term>
, we can find and address conceptual
|
#9887
Using this visualization method, we can find and address conceptual and practical problems in an MT system. |
|
semantic-head-driven generation
</term>
emerge from this
|
method
|
. With a parsimonious
<term>
instantiation
|
#20924
Chart-like parsing and semantic-head-driven generation emerge from this method. |
|
</term>
of the
<term>
adjoining words
</term>
. The
|
method
|
accurately determines that a
<term>
homophone
|
#20485
The method accurately determines that a homophone is misused in a compound noun if one or both of its neighbors is not a member of the semantic set defined by the homophone. |
tech,1-2-P05-3025,bq |
translating a sentence
</term>
. The
<term>
|
method
|
</term>
allows a
<term>
user
</term>
to explore
|
#9849
Themethod allows a user to explore a model of syntax-based statistical machine translation (MT), to understand the model's strengths and weaknesses, and to compare it to other MT systems. |
tech,10-5-H05-1095,bq |
that demonstrate how the proposed
<term>
|
method
|
</term>
allows to better generalize from
|
#7424
Experimental results are presented, that demonstrate how the proposedmethod allows to better generalize from the training data. |
|
</term>
or a
<term>
decision tree
</term>
. The
|
method
|
amounts to tagging
<term>
LMs
</term>
with
<term>
|
#1173
The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. |
measure(ment),5-4-P05-2016,bq |
</term>
. We also refer to an
<term>
evaluation
|
method
|
</term>
and plan to compare our
<term>
system
|
#9817
We also refer to an evaluation method and plan to compare our system's output with a benchmark system. |
tech,5-3-I05-5003,bq |
also introduce a novel
<term>
classification
|
method
|
</term>
based on
<term>
PER
</term>
which leverages
|
#8373
We also introduce a novel classification method based on PER which leverages part of speech information of the words contributing to the word matches and non-matches in the sentence. |
tech,16-3-H05-1095,bq |
phrases
</term>
, as well as a
<term>
training
|
method
|
</term>
based on the maximization of
<term>
|
#7387
A statistical translation model is also presented that deals such phrases, as well as a training method based on the maximization of translation accuracy, as measured with the NIST evaluation metric. |
|
<term>
non-parallel corpus
</term>
. Thus , our
|
method
|
can be applied with great benefit to
<term>
|
#9103
Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available. |
|
</term>
in
<term>
compound nouns
</term>
. This
|
method
|
can not only detect
<term>
Japanese homophone
|
#20421
This method can not only detect Japanese homophone errors in compound nouns, but also can find the correct candidates for the detected errors automatically. |
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. |
|
</term>
of
<term>
training data
</term>
. The
|
method
|
combines
<term>
domain independent acoustic
|
#2224
The method combines domain independent acoustic models with off-the-shelf classifiers to give utterance classification performance that is surprisingly close to what can be achieved using conventional word-trigram recognition requiring manual transcription. |
tech,5-2-C94-1082,bq |
uses a robust
<term>
island-based parsing
|
method
|
</term>
controlled by
<term>
user-defined performance
|
#21120
The system uses a robust island-based parsing method controlled by user-defined performance thresholds. |
|
express opinion . In our experiment , the
|
method
|
could construct a
<term>
corpus
</term>
consisting
|
#11460
In our experiment, the method could construct a corpus consisting of 126,610 sentences. |
|
another 23 subjects showed that the proposed
|
method
|
could effectively generate proper
<term>
|
#5721
The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions. |
|
<term>
WSD system
</term>
, implementing the
|
method
|
described herein showed very encouraging
|
#6508
The evaluation of the WSD system, implementing the method described herein showed very encouraging results. |