#210To 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.
other,8-3-H01-1040,ak
results of a preliminary ,
<term>
qualitative
user
evaluation
</term>
of the
<term>
system
</term>
#353We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to make users aware of the increased potential of IE-enhanced text browsers.
other,31-3-H01-1040,ak
to be done on the interface to make
<term>
users
</term>
aware of the increased potential
#375We also report results of a preliminary, qualitative user evaluation of the system, which while broadly positive indicates further work needs to be done on the interface to makeusers aware of the increased potential of IE-enhanced text browsers.
other,14-2-H01-1049,ak
agents
</term>
that mediate between
<term>
users
</term>
and
<term>
information sources
</term>
#809We integrate a spoken language understanding system with intelligent mobile agents that mediate betweenusers and information sources.
other,22-2-H01-1055,ak
</term>
understand more of what the
<term>
user
</term>
tells them , they need to be more
#952However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what theuser tells them, they need to be more sophisticated at responding to the user.
other,36-2-H01-1055,ak
sophisticated at responding to the
<term>
user
</term>
. The issue of
<term>
system response
#966However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to theuser.
other,6-3-H01-1055,ak
issue of
<term>
system response
</term>
to
<term>
users
</term>
has been extensively studied by the
#974The issue of system response tousers has been extensively studied by the natural language generation community, though rarely in the context of dialog systems.
measure(ment),4-2-H01-1068,ak
systems
</term>
. The three tiers measure
<term>
user
satisfaction
</term>
,
<term>
system support
#1211The three tiers measureuser satisfaction, system support of mission success and component performance.
use of this approach in numerous fielded
user
studies conducted with the U.S. military
#1233We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
other,22-2-P01-1070,ak
target variables which represent a
<term>
user
's informational goals
</term>
. We report
#2166These models, which are built from shallow linguistic features of questions, are employed to predict target variables which represent auser's informational goals.
multilingual , multimedia data . It gives
users
the ability to spend their time finding
#3607It gives users the ability to spend their time finding more data relevant to their task, and gives them translingual reach into other languages by leveraging human language technology.
other,7-2-P03-1031,ak
the
<term>
system
</term>
to understand
<term>
user
utterances
</term>
based on the
<term>
context
#4146This process enables the system to understanduser utterances based on the context of a dialogue.
other,12-3-P03-1031,ak
result
</term>
can be obtained for a
<term>
user
utterance
</term>
due to the
<term>
ambiguity
#4168Since multiple candidates for the understanding result can be obtained for auser utterance due to the ambiguity of speech understanding, it is not appropriate to decide on a single understanding result after each user utterance.
other,35-3-P03-1031,ak
understanding result
</term>
after each
<term>
user
utterance
</term>
. By holding multiple
<term>
#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.
tech,3-1-P03-1033,ak
effective . We address appropriate
<term>
user
modeling
</term>
in order to generate
<term>
#4284We address appropriateuser modeling in order to generate cooperative responses to each user in spoken dialogue systems.
<term>
cooperative responses
</term>
to each
user
in
<term>
spoken dialogue systems
</term>
.
#4294We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems.
other,6-2-P03-1033,ak
Unlike previous studies that focus on
<term>
user
's knowledge
</term>
or typical kinds of
<term>
#4306Unlike previous studies that focus onuser's knowledge or typical kinds of users, the user model we propose is more comprehensive.
other,13-2-P03-1033,ak
knowledge
</term>
or typical kinds of
<term>
users
</term>
, the
<term>
user model
</term>
we propose
#4313Unlike previous studies that focus on user's knowledge or typical kinds ofusers, the user model we propose is more comprehensive.
model,16-2-P03-1033,ak
typical kinds of
<term>
users
</term>
, the
<term>
user
model
</term>
we propose is more comprehensive
#4316Unlike previous studies that focus on user's knowledge or typical kinds of users, theuser model we propose is more comprehensive.
model,8-3-P03-1033,ak
up three
<term>
dimensions
</term>
of
<term>
user
models
</term>
:
<term>
skill level
</term>
to
#4332Specifically, we set up three dimensions ofuser models: skill level to the system, knowledge level on the target domain and the degree of hastiness.