<term>
dialogue systems
</term>
which all Communicator
#243To 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 infrastructurefor dialogue systems which all Communicator participants are using.
describe the features of and requirements
for
a genuinely useful
<term>
software infrastructure
#264In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose.
useful
<term>
software infrastructure
</term>
for
this purpose . In this paper we show how
#270In this presentation, we describe the features of and requirements for a genuinely useful software infrastructurefor this purpose.
<term>
translation output
</term>
sufficient
for
content understanding of the
<term>
original
#536Having been trained on Korean newspaper articles on missiles and chemical biological warfare, the system produces the translation output sufficient for content understanding of the original document.
evaluation techniques
</term>
, originally devised
for
the
<term>
evaluation
</term>
of
<term>
human
#562The 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.
Listen-Communicate-Show ( LCS )
</term>
is a new paradigm
for
<term>
human interaction with data sources
#788Listen-Communicate-Show (LCS) is a new paradigm for human interaction with data sources.
a
<term>
mobile , intelligent agent
</term>
for
execution at the appropriate
<term>
database
#857The request is passed to a mobile, intelligent agentfor execution at the appropriate database.
experimental results that clearly show the need
for
a
<term>
dynamic language model combination
#1140We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further.
</term>
. We describe a three-tiered approach
for
<term>
evaluation
</term>
of
<term>
spoken dialogue
#1200We describe a three-tiered approach for evaluation of spoken dialogue systems.
</term>
and
<term>
error-correction rules
</term>
for
<term>
Thai key prediction
</term>
and
<term>
#1253This paper proposes a practical approach employing n-gram models and error-correction rulesfor Thai key prediction and Thai-English language identification.
choice of
<term>
syntactic structure
</term>
for
<term>
elementary speech acts
</term>
and the
#1317Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structurefor elementary speech acts and the decision of how to combine them into one or more sentences.
sentence planner
</term>
, and a new methodology
for
automatically training
<term>
SPoT
</term>
#1351In 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.
list of possible
<term>
sentence plans
</term>
for
a given
<term>
text-plan input
</term>
. Second
#1394First, a very simple, randomized sentence-plan-generator (SPG) generates a potentially large list of possible sentence plansfor a given text-plan input.
worst-case parsing time complexity
</term>
.
For
example , after
<term>
translation
</term>
#1655In particular, range concatenation languages [RCL] can be parsed in polynomial time and many classical grammatical formalisms can be translated into equivalent RCGs without increasing their worst-case parsing time complexity. For example, after translation into an equivalent RCG, any tree adjoining grammar can be parsed in O(n6) time.
choices
</term>
of the
<term>
main parser
</term>
for
a
<term>
language L
</term>
are directed by
#1708The non-deterministic parsing choices of the main parserfor a language L are directed by a guide which uses the shared derivation forest output by a prior RCL parser for a suitable superset of L .
output by a prior
<term>
RCL parser
</term>
for
a suitable
<term>
superset
</term>
of L . The
#1729The non-deterministic parsing choices of the main parser for a language L are directed by a guide which uses the shared derivation forest output by a prior RCL parserfor a suitable superset of L .
<term>
paraphrasing
</term>
is critical both
for
<term>
interpretation and generation of natural
#1759While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases.
<term>
unsupervised learning algorithm
</term>
for
<term>
identification of paraphrases
</term>
#1784We present an unsupervised learning algorithmfor identification of paraphrases from a corpus of multiple English translations of the same source text.
</term>
. This paper presents a formal analysis
for
a large class of
<term>
words
</term>
called
#1822This paper presents a formal analysis for a large class of words called alternative markers, which includes other (than), such (as), and besides.