other,8-1-H01-1017,bq |
in robust ,
<term>
mixed-initiative speech
|
dialogue
|
interactions
</term>
which reach beyond current
|
#216
To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. |
tech,18-1-H01-1017,bq |
reach beyond current capabilities in
<term>
|
dialogue
|
systems
</term>
, the
<term>
DARPA Communicator
|
#224
To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities indialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. |
tech,38-1-H01-1017,bq |
message-passing infrastructure
</term>
for
<term>
|
dialogue
|
systems
</term>
which all
<term>
Communicator
|
#244
To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure fordialogue systems which all Communicator participants are using. |
tech,8-1-H01-1068,bq |
for
<term>
evaluation
</term>
of
<term>
spoken
|
dialogue
|
systems
</term>
. The three tiers measure
|
#1204
We describe a three-tiered approach for evaluation of spoken dialogue systems. |
tech,12-2-P01-1056,bq |
sentence planner
</term>
for a
<term>
spoken
|
dialogue
|
system
</term>
by eliciting
<term>
subjective
|
#2063
In this paper We experimentally evaluate a trainable sentence planner for a spoken dialogue system by eliciting subjective human judgments. |
tech,16-1-N03-3010,bq |
language understanding
</term>
in a
<term>
|
dialogue
|
system
</term>
. We build this based on both
|
#3493
In this paper, we propose a novel Cooperative Model for natural language understanding in adialogue system. |
other,11-1-P03-1022,bq |
<term>
pronoun resolution
</term>
in
<term>
spoken
|
dialogue
|
</term>
. Our
<term>
system
</term>
deals with
|
#3985
We apply a decision tree based approach to pronoun resolution in spoken dialogue. |
other,11-3-P03-1022,bq |
<term>
pronoun resolution
</term>
in
<term>
spoken
|
dialogue
|
</term>
and determine the most promising
<term>
|
#4010
We present a set of features designed for pronoun resolution in spoken dialogue and determine the most promising features. |
tech,8-1-P03-1031,bq |
understanding process
</term>
in
<term>
spoken
|
dialogue
|
systems
</term>
. This process enables the
|
#4135
This paper concerns the discourse understanding process in spoken dialogue systems. |
other,15-2-P03-1031,bq |
based on the
<term>
context
</term>
of a
<term>
|
dialogue
|
</term>
. Since multiple
<term>
candidates
</term>
|
#4153
This process enables the system to understand user utterances based on the context of adialogue. |
other,13-4-P03-1031,bq |
resolving the
<term>
ambiguity
</term>
as the
<term>
|
dialogue
|
</term>
progresses , the
<term>
discourse understanding
|
#4205
By holding multiple candidates for understanding results and resolving the ambiguity as thedialogue progresses, the discourse understanding accuracy can be improved. |
lr,15-5-P03-1031,bq |
statistical information
</term>
obtained from
<term>
|
dialogue
|
corpora
</term>
. Unlike conventional methods
|
#4231
This paper proposes a method for resolving this ambiguity based on statistical information obtained fromdialogue corpora. |
tech,15-1-P03-1033,bq |
</term>
to each
<term>
user
</term>
in
<term>
spoken
|
dialogue
|
systems
</term>
. Unlike previous studies
|
#4295
We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems. |
lr,13-4-P03-1033,bq |
decision tree learning
</term>
using real
<term>
|
dialogue
|
data
</term>
collected by the
<term>
system
|
#4364
Moreover, the models are automatically derived by decision tree learning using realdialogue data collected by the system. |
other,21-7-P03-1033,bq |
users
</term>
without increasing the
<term>
|
dialogue
|
duration
</term>
for
<term>
skilled users
</term>
|
#4424
Experimental evaluation shows that the cooperative responses adaptive to individual users serve as good guidance for novice users without increasing thedialogue duration for skilled users. |
other,11-3-P03-1070,bq |
</term>
differed depending on the type of
<term>
|
dialogue
|
move
</term>
being grounded , and the overall
|
#5069
The distribution of nonverbal behaviors differed depending on the type ofdialogue move being grounded, and the overall pattern reflected a monitoring of lack of negative feedback. |
other,18-4-P03-1070,bq |
nonverbal grounding acts
</term>
to update
<term>
|
dialogue
|
state
</term>
. An empirical comparison of
|
#5105
Based on these results, we present an ECA that uses verbal and nonverbal grounding acts to updatedialogue state. |
other,12-1-C04-1035,bq |
<term>
sluice disambiguation
</term>
in
<term>
|
dialogue
|
</term>
. We extract a set of
<term>
heuristic
|
#5161
This paper presents a machine learning approach to bare sluice disambiguation indialogue. |
other,47-1-C04-1128,bq |
the necessary
<term>
segments
</term>
of
<term>
|
dialogue
|
</term>
that would make a
<term>
summary
</term>
|
#6249
While sentence extraction as an approach to summarization has been shown to work in documents of certain genres, because of the conversational nature of email communication where utterances are made in relation to one made previously, sentence extraction may not capture the necessary segments ofdialogue that would make a summary coherent. |
other,10-2-E06-1022,bq |
well the
<term>
addressee
</term>
of a
<term>
|
dialogue
|
act
</term>
can be predicted based on
<term>
|
#10263
First, we investigate how well the addressee of adialogue act can be predicted based on gaze, utterance and conversational context features. |