#257In 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 from
<term>
#277In 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.
via a standard
<term>
text browser
</term>
.
We
describe how this information is used in
#313In 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 prototype system designed to support information workers' access to a pharmaceutical news archive as part of their industry watch function.
part of their industry watch function .
We
also report results of a preliminary ,
<term>
#344We 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. We 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.
browsers
</term>
. At MIT Lincoln Laboratory ,
we
have been developing a
<term>
Korean-to-English
#391At MIT Lincoln Laboratory, we have been developing a Korean-to-English machine translation system CCLINC (Common Coalition Language System at Lincoln Laboratory).
machine translation ( MT ) systems
</term>
.
We
believe that these
<term>
evaluation techniques
#581The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems. We believe that these evaluation techniques will provide information about both the human language learning process, the translation process and the development of machine translation systems.
<term>
assessors
</term>
made their decisions .
We
tested this to see if similar criteria
#662Even more illuminating was the factors on which the assessors made their decisions. We tested this to see if similar criteria could be elicited from duplicating the experiment using machine translation output.
human interaction with data sources
</term>
.
We
integrate a
<term>
spoken language understanding
#795Listen-Communicate-Show (LCS) is a new paradigm for human interaction with data sources. We integrate a spoken language understanding system with intelligent mobile agents that mediate between users and information sources.
</term>
and
<term>
information sources
</term>
.
We
have built and will demonstrate an application
#814We integrate a spoken language understanding system with intelligent mobile agents that mediate between users and information sources. We have built and will demonstrate an application of this approach called LCS-Marine.
when a
<term>
request
</term>
is complete .
We
have demonstrated this capability in several
#887Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete. We have demonstrated this capability in several field exercises with the Marines and are currently developing applications of this technology in new domains.
the context of
<term>
dialog systems
</term>
.
We
show how research in
<term>
generation
</term>
#995The issue of system response to users has been extensively studied by the natural language generation community, though rarely in the context of dialog systems. We 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.
learning techniques
</term>
. In this paper ,
we
address the problem of combining several
#1031In this paper, we address the problem of combining several language models (LMs).
several
<term>
language models ( LMs )
</term>
.
We
find that simple
<term>
interpolation methods
#1044In this paper, we address the problem of combining several language models (LMs). We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of an oracle.
decisions using the
<term>
reference
</term>
.
We
provide experimental results that clearly
#1131Actually, the oracle acts like a dynamic combiner with hard decisions using the reference. We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further.
improve the
<term>
performance
</term>
further .
We
suggest a method that mimics the behavior
#1152We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further. We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree.
</term>
with the best
<term>
confidence
</term>
.
We
describe a three-tiered approach for
<term>
#1195The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. We describe a three-tiered approach for evaluation of spoken dialogue systems.
success and
<term>
component performance
</term>
.
We
describe our use of this approach in numerous
#1223The three tiers measure user satisfaction, system support of mission success and component performance. We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
component performance
</term>
. We describe
our
use of this approach in numerous fielded
#1225We describe our use of this approach in numerous fielded user studies conducted with the U.S. military.
the
<term>
error-correction rules
</term>
.
Our
<term>
algorithm
</term>
reported more than
#1277The paper also proposes rule-reduction algorithm applying mutual information to reduce the error-correction rules. Our algorithm reported more than 99% accuracy in both language identification and key prediction.
more
<term>
sentences
</term>
. In this paper ,
we
present
<term>
SPoT
</term>
, a
<term>
sentence
#1339In 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.