#50The question is, however, how an interesting information piece would be found in a large database.
automatic detection of those activities
in
meeting situation and everyday rejoinders
#119This paper addresses the problem of the automatic detection of those activities in meeting situation and everyday rejoinders.
obtained . To support engaging human users
in
<term>
robust , mixed-initiative speech dialogue
#211To 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.
</term>
which reach beyond current capabilities
in
<term>
dialogue systems
</term>
, the DARPA
#223To 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.
all Communicator participants are using .
In
this presentation , we describe the features
#253To 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. In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose.
infrastructure
</term>
for this purpose .
In
this paper we show how two standard outputs
#274In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose. In this paper we show how two standard outputs from information extraction (IE) systems - named entity annotations and scenario templates - can be used to enhance access to text collections via a standard text browser.
We describe how this information is used
in
a
<term>
prototype system
</term>
designed
#320We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function.
systems
</term>
. This , the first experiment
in
a series of experiments , looks at the
<term>
#614This, the first experiment in a series of experiments, looks at the intelligibility of MT output.
native from non-native language essays
</term>
in
less than 100
<term>
words
</term>
. Even more
#642A language learning experiment showed that assessors can differentiate native from non-native language essaysin less than 100 words.
preliminary analysis of the factors involved
in
the decision making process will be presented
#770The results of this experiment, along with a preliminary analysis of the factors involved in the decision making process will be presented here.
complete . We have demonstrated this capability
in
several field exercises with the Marines
#892We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains.
developing applications of this technology
in
new domains . Recent advances in
<term>
Automatic
#907We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains.
technology in new domains . Recent advances
in
<term>
Automatic Speech Recognition technology
#913Recent advances in Automatic Speech Recognition technology have put the goal of naturally sounding dialog systems within reach.
generation community
</term>
, though rarely
in
the context of
<term>
dialog systems
</term>
#988The issue of system response to users has been extensively studied by the natural language generation community, though rarely in the context of dialog systems.
dialog systems
</term>
. We show how research
in
<term>
generation
</term>
can be adapted to
#999We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques.
<term>
machine learning techniques
</term>
.
In
this paper , we address the problem of
#1027We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques. In this paper, we address the problem of combining several language models (LMs).
</term>
. We describe our use of this approach
in
numerous fielded user studies conducted
#1230We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
reported more than 99 %
<term>
accuracy
</term>
in
both
<term>
language identification
</term>
#1285Our algorithm reported more than 99% accuracyin both language identification and key prediction.
into one or more
<term>
sentences
</term>
.
In
this paper , we present
<term>
SPoT
</term>
#1335Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. In this paper, we present SPoT, a sentence planner, and a new methodology for automatically training SPoT on the basis of feedback provided by human judges.
<term>
top human-ranked sentence plan
</term>
.
In
this paper , we compare the relative effects
#1461We show that the trained SPR learns to select a sentence plan whose rating on average is only 5% worse than the top human-ranked sentence plan. In this paper, we compare the relative effects of segment order, segmentation and segment contiguity on the retrieval performance of a translation memory system.