|
describe an efficient
<term>
decoder
</term>
and
|
show
|
that using these
<term>
tree-based models
|
#9279
We describe an efficient decoder and show that using these tree-based models in combination with conventional SMT models provides a promising approach that incorporates the power of phrasal SMT with the linguistic generality available in a parser. |
|
and generate
<term>
paraphrases
</term>
. We
|
show
|
that this task can be done using
<term>
bilingual
|
#9668
We show that this task can be done using bilingual parallel corpora, a much more commonly available resource. |
|
statistical machine translation
</term>
, we
|
show
|
how
<term>
paraphrases
</term>
in one
<term>
|
#9697
Using alignment techniques from phrase-based statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot. |
|
<term>
translation probabilities
</term>
, and
|
show
|
how it can be refined to take
<term>
contextual
|
#9738
We define a paraphrase probability that allows paraphrases extracted from a bilingual parallel corpus to be ranked using translation probabilities, and show how it can be refined to take contextual information into account. |
|
information
</term>
. The
<term>
classifiers
</term>
|
show
|
little
<term>
gain
</term>
from information
|
#10314
The classifiersshow little gain from information about meeting context. |
|
quadratic time
</term>
. Furthermore , we will
|
show
|
how some
<term>
evaluation measures
</term>
|
#10389
Furthermore, we will show how some evaluation measures can be improved by the introduction of word-dependent substitution costs. |
|
pairs
</term>
. The experimental results will
|
show
|
that it significantly outperforms state-of-the-art
|
#10428
The experimental results will show that it significantly outperforms state-of-the-art approaches in sentence-level correlation. |
|
Begin/After tagging
</term>
or
<term>
BIA
</term>
, and
|
show
|
that it is competitive to the best other
|
#10854
We also introduce a new strategy, called Begin/After tagging or BIA, and show that it is competitive to the best other strategies. |
|
the algorithm on a
<term>
corpus
</term>
, and
|
show
|
that it reduces the degree of
<term>
ambiguity
|
#11186
We evaluate the algorithm on a corpus, and show that it reduces the degree of ambiguity significantly while taking negligible runtime. |
|
Experiment results on
<term>
ACE corpora
</term>
|
show
|
that this
<term>
spectral clustering based
|
#11379
Experiment results on ACE corporashow that this spectral clustering based approach outperforms the other clustering methods. |
|
</term>
. A series of tests are described that
|
show
|
the power of the
<term>
error correction
|
#14067
A series of tests are described that show the power of the error correction methodology when stereotypic dialogue occurs. |
|
of
<term>
monolingual UCG
</term>
, we will
|
show
|
how the two can be integrated , and present
|
#15139
After introducing this approach to MT system design, and the basics of monolingual UCG, we will show how the two can be integrated, and present an example from an implemented bi-directional Engllsh-Spanish fragment. |
|
examine a broad range of
<term>
texts
</term>
to
|
show
|
how the distribution of
<term>
demonstrative
|
#15201
We examine a broad range of texts to show how the distribution of demonstrative forms and functions is genre dependent. |
|
previous papers [ Zernik87 ] . Second , we
|
show
|
in this paper how a
<term>
lexical hierarchy
|
#15871
Second, we show in this paper how a lexical hierarchy is used in predicting new linguistic concepts. |
|
</term>
and
<term>
synthesis system
</term>
. We
|
show
|
that the proposed approach is more describable
|
#16404
We show that the proposed approach is more describable than other approaches such as those employing a traditional generative phonological approach. |
|
corpus
</term>
. The results of the experiment
|
show
|
that in most of the cases the
<term>
cooccurrence
|
#16696
The results of the experiment show that in most of the cases the cooccurrence statistics indeed reflect the semantic constraints and thus provide a basis for a useful disambiguation tool. |
|
<term>
training speakers
</term>
. Second , we
|
show
|
a significant improvement for
<term>
speaker
|
#17122
Second, we show a significant improvement for speaker adaptation (SA) using the new SI corpus and a small amount of speech from the new (target) speaker. |
|
combinatorics of
<term>
free indexation
</term>
, we
|
show
|
that the problem of enumerating all possible
|
#17372
First, by investigating the combinatorics of free indexation, we show that the problem of enumerating all possible indexings requires exponential time. |
|
Chinese names without title
</term>
. We will
|
show
|
the experimental results for two
<term>
corpora
|
#18340
We will show the experimental results for two corpora and compare them with the results by the NTHU's statistic-based system, the only system that we know has attacked the same problem. |
|
on all four applications are provided to
|
show
|
the effectiveness of the
<term>
MAP estimation
|
#19144
New experimental results on all four applications are provided to show the effectiveness of the MAP estimation approach. |