#339We 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.
factors on which the
<term>
assessors
</term>
made
their
decisions . We tested this to see if similar
#659Even more illuminating was the factors on which the assessors made their decisions.
minutes per extract to determine whether
they
believed the sample output to be an
<term>
#723The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translation or a machine translation.
machine translation
</term>
. Additionally ,
they
were asked to mark the
<term>
word
</term>
#741Additionally, they were asked to mark the word at which they made this decision.
asked to mark the
<term>
word
</term>
at which
they
made this decision . The results of this
#750Additionally, they were asked to mark the word at which they made this decision.
</term>
, tactical personnel can converse with
their
logistics system to place a
<term>
supply
#836Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request.
instruct the
<term>
system
</term>
to notify
them
when the status of a
<term>
request
</term>
#872Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete.
understand more of what the
<term>
user
</term>
tells
them
, they need to be more sophisticated at
#954However, 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.
of what the
<term>
user
</term>
tells them ,
they
need to be more sophisticated at responding
#956However, 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.
</term>
and the decision of how to combine
them
into one or more
<term>
sentences
</term>
.
#1328Sentence 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.
<term>
word N-gram models
</term>
. Further , in
their
optimum configuration ,
<term>
bag-of-words
#1562Further,in their optimum configuration, bag-of-words methods are shown to be equivalent to segment order-sensitive methods in terms of retrieval accuracy, but much faster.
equivalent
<term>
RCGs
</term>
without increasing
their
<term>
worst-case parsing time complexity
#1649In 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.
poorly on
<term>
queries
</term>
containing
them
. I show that the
<term>
performance
</term>
#1870These words appear frequently enough in dialog to warrant serious attention, yet present natural language search engines perform poorly on queries containing them.
recognition hypotheses ( SRH )
</term>
in terms of
their
<term>
semantic coherence
</term>
. We conducted
#2476We apply our system to the task of scoring alternative speech recognition hypotheses (SRH) in terms of their semantic coherence.
data . It gives users the ability to spend
their
time finding more data relevant to their
#3612It 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.
their time finding more data relevant to
their
task , and gives them translingual reach
#3619It 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.
data relevant to their task , and gives
them
translingual reach into other
<term>
languages
#3624It 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.
several levels of both
<term>
chunks
</term>
and
their
<term>
relations
</term>
, and then efficiently
#3819The HDAG Kernel directly accepts several levels of both chunks and their relations, and then efficiently computes the weighed sum of the number of common attribute sequences of the HDAGs.
manually sense-tagged data
</term>
have in
their
sense coverage . Our analysis also highlights
#4913On a subset of the most difficult SENSEVAL-2 nouns, the accuracy difference between the two approaches is only 14.0%, and the difference could narrow further to 6.5% if we disregard the advantage that manually sense-tagged data have in their sense coverage.
</term>
, are now well established . Yet ,
they
are scarcely used for the assessment of
#6245Yet, they are scarcely used for the assessment of language pairs like English-Chinese or English-Japanese, because of the word segmentation problem.