#1243This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification.
language identification
</term>
. The paper also
proposes
<term>
rule-reduction algorithm
</term>
applying
#1265The paper also proposes rule-reduction algorithm applying mutual information to reduce the error-correction rules.
language generator
</term>
have recently been
proposed
, but a fundamental concern is whether
#2026Techniques 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.
a
<term>
baseline
</term>
of 54.55 % ) . We
propose
a new
<term>
phrase-based translation model
#2541We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models.
evaluate and compare several , previously
proposed
<term>
phrase-based translation models
</term>
#2560We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models.
output selection
</term>
. Furthermore , we
propose
the use of standard
<term>
parser evaluation
#2842Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems.
phrase length
</term>
. In this paper , we
propose
a novel
<term>
Cooperative Model
</term>
for
#3483In this paper, we propose a novel Cooperative Model for natural language understanding in a dialogue system.
quality
<term>
IE results
</term>
. This paper
proposes
the
<term>
Hierarchical Directed Acyclic
#3792This paper proposes the Hierarchical Directed Acyclic Graph (HDAG) Kernel for structured natural language data.
of the
<term>
HDAGs
</term>
. We applied the
proposed
method to
<term>
question classification
</term>
#3843We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function.
A novel
<term>
evaluation scheme
</term>
is
proposed
which accounts for the effect of
<term>
polysemy
#3945A novel evaluation scheme is proposed which accounts for the effect of polysemy on the clusters, offering us a good insight into the potential and limitations of semantically classifying undisambiguated SCF data.
accuracy
</term>
can be improved . This paper
proposes
a method for resolving this
<term>
ambiguity
#4220This paper proposes a method for resolving this ambiguity based on statistical information obtained from dialogue corpora.
use
<term>
hand-crafted rules
</term>
, the
proposed
method enables easy design of the
<term>
#4245Unlike conventional methods that use hand-crafted rules, the proposed method enables easy design of the discourse understanding process.
that a
<term>
system
</term>
that exploits the
proposed
method performs sufficiently and that holding
#4266Experiment results have shown that a system that exploits the proposed method performs sufficiently and that holding multiple candidates for understanding results is effective.
users
</term>
, the
<term>
user model
</term>
we
propose
is more comprehensive . Specifically ,
#4319Unlike previous studies that focus on user's knowledge or typical kinds of users, the user model we propose is more comprehensive.
means
</term>
for
<term>
grounding
</term>
, and
propose
a design for
<term>
embodied conversational
#5020We investigate the verbal and nonverbal means for grounding, and propose a design for embodied conversational agents that relies on both kinds of signals to establish common ground in human-computer interaction.
from a
<term>
word-aligned corpora
</term>
is
proposed
. A
<term>
statistical translation model
</term>
#5612A method for producing such phrases from a word-aligned corpora is proposed.
are presented , that demonstrate how the
proposed
method allows to better generalize from
#5667Experimental results are presented, that demonstrate how the proposed method allows to better generalize from the training data.
right-side dependencies
</term>
. This paper
proposes
a
<term>
two-phase shift-reduce dependency
#6677This paper proposes a two-phase shift-reduce dependency parser based on SVM learning.
Phase II . In experimental evaluation , our
proposed
method outperforms previous
<term>
shift-reduce
#6716In experimental evaluation, our proposed method outperforms previous shift-reduce dependency parsers for the Chine language, showing improvement of dependency accuracy by 10.08%.
conceptual cohesion
</term>
. In this paper , we
propose
and implement a model for bootstrapping
#7105In this paper, we propose and implement a model for bootstrapping parallel wordnets based on one monolingual wordnet and a set of cross-lingual lexical semantic relations.