|
language generator
</term>
have recently been
|
proposed
|
, but a fundamental concern is whether
|
#2025
Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches. |
|
from a
<term>
word-aligned corpora
</term>
is
|
proposed
|
. A
<term>
statistical translation model
</term>
|
#7368
A method for producing such phrases from a word-aligned corpora is proposed. |
|
approach to restricted-domain parsing
</term>
is
|
proposed
|
. In this approach , the definitions of
|
#13329
An entity-oriented approach to restricted-domain parsing is proposed. |
|
</term>
for
<term>
Horn logic program
</term>
is
|
proposed
|
. It is also a drastic generalization of
|
#20889
A new, flexible inference method for Horn logic program is proposed. |
|
modification of the
<term>
document
</term>
is
|
proposed
|
. The explanation of an
<term>
ambiguity
</term>
|
#15659
A new approach for Interactive Machine Translation where the author interacts during the creation or the modification of the document is proposed. |
|
relations
</term>
between
<term>
segments
</term>
is
|
proposed
|
. This method is precise and
<term>
computationally
|
#17774
In this paper discourse segments are defined and a method for discourse segmentation primarily based on abduction of temporal relations between segments is proposed. |
|
<term>
part-of-speech-based criterion
</term>
is
|
proposed
|
. We postulate that
<term>
source texts
</term>
|
#20554
Rather than using length-based or translation-based criterion, a part-of-speech-based criterion is proposed. |
|
real-time response
</term>
. We have already
|
proposed
|
a model ,
<term>
TDMT ( Transfer-Driven Machine
|
#20231
We have already proposed a model, TDMT (Transfer-Driven Machine Translation), that translates a sentence utilizing examples effectively and performs accurate structural disambiguation and target word selection. |
|
accuracy rate
</term>
directly . To make the
|
proposed
|
algorithm robust , the possible variations
|
#17883
To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members. |
|
synthesis system
</term>
. We show that the
|
proposed
|
approach is more describable than other
|
#16407
We show that the proposed approach is more describable than other approaches such as those employing a traditional generative phonological approach. |
|
the concept of
<term>
sublanguage
</term>
, is
|
proposed
|
for identifying
<term>
unknown words
</term>
|
#18301
In this paper, a new mechanism, based on the concept of sublanguage, is proposed for identifying unknown words, especially personal names, in Chinese newspapers. |
|
We first apply approaches that have been
|
proposed
|
for
<term>
predicting top-level topic shifts
|
#10495
We first apply approaches that have been proposed for predicting top-level topic shifts to the problem of identifying subtopic boundaries. |
|
use different
<term>
dialog schemata
</term>
|
proposed
|
in empirical
<term>
conversation analysis
|
#12382
as a device to represent and to use different dialog schemataproposed in empirical conversation analysis; |
|
, in
<term>
Chinese newspapers
</term>
. The
|
proposed
|
mechanism includes
<term>
title-driven name
|
#18316
The proposed mechanism includes title-driven name recognition, adaptive dynamic word formation, identification of 2-character and 3-character Chinese names without title. |
|
are presented , that demonstrate how the
|
proposed
|
<term>
method
</term>
allows to better generalize
|
#7423
Experimental results are presented, that demonstrate how the proposed method allows to better generalize from the training data. |
|
using another 23 subjects showed that the
|
proposed
|
method could effectively generate proper
|
#5720
The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions. |
|
use
<term>
hand-crafted rules
</term>
, the
|
proposed
|
<term>
method
</term>
enables easy design of
|
#4243
Unlike conventional methods that use hand-crafted rules, the proposed method enables easy design of the discourse understanding process. |
|
<term>
synonymous expressions
</term>
. Our
|
proposed
|
method improves the
<term>
accuracy
</term>
|
#6184
Our proposed method improves the accuracy of our term aggregation system, showing that our approach is successful. |
|
pairs
</term>
. Our study reveals that the
|
proposed
|
method not only reduces an extensive system
|
#5824
Our study reveals that the proposed method not only reduces an extensive system development effort but also improves the transliteration accuracy significantly. |
|
that a
<term>
system
</term>
that exploits the
|
proposed
|
<term>
method
</term>
performs sufficiently
|
#4264
Experiment results have shown that a system that exploits the proposed method performs sufficiently and that holding multiple candidates for understanding results is effective. |