<term>
histogram
</term>
of
<term>
keywords
</term>
as
the
<term>
document representation
</term>
#64Traditional information retrieval techniques use a histogram of keywordsas the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance.
offer additional
<term>
indices
</term>
such
as
the time and place of the rejoinder and
#76Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance.
<term>
index
</term>
could be the activity such
as
discussing , planning , informing , story-telling
#96An alternative index could be the activity such as discussing, planning, informing, story-telling, etc.
Emotions and other
<term>
indices
</term>
such
as
the dominance distribution of speakers
#168Emotions and other indices such as the dominance distribution of speakers might be available on the surface and could be used directly.
<term>
pharmaceutical news archive
</term>
as
part of their industry watch function .
#336We describe how this information is used in a prototype system designed to support information workers' access to a pharmaceutical news archiveas part of their industry watch function.
</term>
has brought to light a new problem :
as
<term>
dialog systems
</term>
understand more
#944However, 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 the user.
and single word lexical paraphrases
</term>
as
well as
<term>
syntactic paraphrases
</term>
#1810Our approach yields phrasal and single word lexical paraphrasesas well as syntactic paraphrases.
single word lexical paraphrases
</term>
as well
as
<term>
syntactic paraphrases
</term>
. This
#1812Our approach yields phrasal and single word lexical paraphrases as well as syntactic paraphrases.
, which includes other ( than ) , such (
as
) , and besides . These
<term>
words
</term>
#1841This paper presents a formal analysis for a large class of words called alternative markers, which includes other (than), such ( as), and besides.
</term>
. The value of this approach is that
as
the
<term>
operational semantics
</term>
of
#1911The value of this approach is that as the operational semantics of natural language applications improve, even larger improvements are possible.
Montague semantics
</term>
which can be viewed
as
a formal computation of the logical form
#2004Here we emphasize the connection to Montague semantics which can be viewed as a formal computation of the logical form.
</term>
and the
<term>
baselines
</term>
, and
as
well as the
<term>
hand-crafted system
</term>
#2118We show that the trainable sentence planner performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.
and the
<term>
baselines
</term>
, and as well
as
the
<term>
hand-crafted system
</term>
. We
#2120We show that the trainable sentence planner performs better than the rule-based systems and the baselines, and as well as the hand-crafted system.
German corpus
</term>
of 2.284
<term>
SRHs
</term>
as
either coherent or incoherent ( given a
#2526An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHsas either coherent or incoherent (given a baseline of 54.55%).
</term>
for
<term>
word alignment
</term>
, known
as
the
<term>
cohesion constraint
</term>
. It
#3239We present a syntax-based constraint for word alignment, known as the cohesion constraint.
bootstrapping procedure
</term>
is implemented
as
training two
<term>
successive learners
</term>
#3340The bootstrapping procedure is implemented as training two successive learners.
tasks
</term>
to evaluate its performance
as
a
<term>
similarity measure
</term>
and a
<term>
#3856We applied the proposed method to question classification and sentence alignment tasks to evaluate its performance as a similarity measure and a kernel function.
<term>
Link detection
</term>
has been regarded
as
a core technology for the
<term>
Topic Detection
#4048Link detection has been regarded as a core technology for the Topic Detection and Tracking tasks of new event detection.
</term>
and
<term>
new event detection
</term>
as
<term>
information retrieval task
</term>
and
#4076In this paper we formulate story link detection and new event detectionas information retrieval task and hypothesize on the impact of precision and recall on both systems.
</term>
and resolving the
<term>
ambiguity
</term>
as
the
<term>
dialogue
</term>
progresses , the
#4205By holding multiple candidates for understanding results and resolving the ambiguityas the dialogue progresses, the discourse understanding accuracy can be improved.