</term>
. Since multiple
<term>
candidates
</term>
#4154This process enables the system to understand user utterances based on the context of adialogue.
other,31-3-P03-1031,ak
appropriate to decide on a single
<term>
understanding result
</term>
after each
<term>
user utterance
</term>
#4187Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity of speech understanding, it is not appropriate to decide on a singleunderstanding result after each user utterance.
other,35-3-P03-1031,ak
understanding result
</term>
after each
<term>
user utterance
</term>
. By holding multiple
<term>
candidates
#4191Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity of speech understanding, it is not appropriate to decide on a single understanding result after eachuser utterance.
other,13-4-P03-1031,ak
resolving the
<term>
ambiguity
</term>
as the
<term>
dialogue
</term>
progresses , the
<term>
discourse understanding
#4207By holding multiple candidates for understanding results and resolving the ambiguity as thedialogue progresses, the discourse understanding accuracy can be improved.
other,20-7-P03-1031,ak
multiple
<term>
candidates
</term>
for
<term>
understanding results
</term>
is effective . We address appropriate
#4276Experiment results have shown that a system that exploits the proposed method performs sufficiently and that holding multiple candidates forunderstanding results is effective.
measure(ment),17-4-P03-1031,ak
<term>
dialogue
</term>
progresses , the
<term>
discourse understanding accuracy
</term>
can be improved . This paper proposes
#4211By holding multiple candidates for understanding results and resolving the ambiguity as the dialogue progresses, thediscourse understanding accuracy can be improved.
other,8-5-P03-1031,ak
proposes a method for resolving this
<term>
ambiguity
</term>
based on
<term>
statistical information
#4226This paper proposes a method for resolving thisambiguity based on statistical information obtained from dialogue corpora.
tech,4-2-P03-1031,ak
systems
</term>
. This process enables the
<term>
system
</term>
to understand
<term>
user utterances
#4143This process enables thesystem to understand user utterances based on the context of a dialogue.
other,5-3-P03-1031,ak
multiple
<term>
candidates
</term>
for the
<term>
understanding result
</term>
can be obtained for a
<term>
user utterance
#4161Since multiple candidates for theunderstanding result can be obtained for a user utterance due to the ambiguity of speech understanding, it is not appropriate to decide on a single understanding result after each user utterance.
tech,19-3-P03-1031,ak
due to the
<term>
ambiguity
</term>
of
<term>
speech understanding
</term>
, it is not appropriate to decide
#4175Since multiple candidates for the understanding result can be obtained for a user utterance due to the ambiguity ofspeech understanding, it is not appropriate to decide on a single understanding result after each user utterance.
other,12-2-P03-1031,ak
user utterances
</term>
based on the
<term>
context
</term>
of a
<term>
dialogue
</term>
. Since
#4151This process enables the system to understand user utterances based on thecontext of a dialogue.
tech,6-7-P03-1031,ak
Experiment results have shown that a
<term>
system
</term>
that exploits the proposed method
#4262Experiment results have shown that asystem that exploits the proposed method performs sufficiently and that holding multiple candidates for understanding results is effective.
lr,15-5-P03-1031,ak
statistical information
</term>
obtained from
<term>
dialogue corpora
</term>
. Unlike conventional methods that
#4233This paper proposes a method for resolving this ambiguity based on statistical information obtained fromdialogue corpora.
other,7-2-P03-1031,ak
the
<term>
system
</term>
to understand
<term>
user utterances
</term>
based on the
<term>
context
</term>
of
#4146This process enables the system to understanduser utterances based on the context of a dialogue.
other,4-1-P03-1031,ak
hypothesis . This paper concerns the
<term>
discourse understanding process
</term>
in
<term>
spoken dialogue systems
</term>
#4131This paper concerns thediscourse understanding process in spoken dialogue systems.
other,18-7-P03-1031,ak
sufficiently and that holding multiple
<term>
candidates
</term>
for
<term>
understanding results
</term>
#4274Experiment results have shown that a system that exploits the proposed method performs sufficiently and that holding multiplecandidates for understanding results is effective.
model,5-6-P03-1031,ak
Unlike conventional methods that use
<term>
hand-crafted rules
</term>
, the proposed method enables easy
#4241Unlike conventional methods that usehand-crafted rules, the proposed method enables easy design of the discourse understanding process.
other,11-5-P03-1031,ak
this
<term>
ambiguity
</term>
based on
<term>
statistical information
</term>
obtained from
<term>
dialogue corpora
#4229This paper proposes a method for resolving this ambiguity based onstatistical information obtained from dialogue corpora.
other,5-4-P03-1031,ak
multiple
<term>
candidates
</term>
for
<term>
understanding results
</term>
and resolving the
<term>
ambiguity
</term>
#4199By holding multiple candidates forunderstanding results and resolving the ambiguity as the dialogue progresses, the discourse understanding accuracy can be improved.
other,17-3-P03-1031,ak
<term>
user utterance
</term>
due to the
<term>
ambiguity
</term>
of
<term>
speech understanding
</term>
#4173Since multiple candidates for the understanding result can be obtained for a user utterance due to theambiguity of speech understanding, it is not appropriate to decide on a single understanding result after each user utterance.