|
converse with their logistics system to place
|
a
|
supply or information request . The request
|
#841
Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request. |
|
information request . The request is passed to
|
a
|
<term>
mobile , intelligent agent
</term>
for
|
#852
The request is passed to a mobile, intelligent agent for execution at the appropriate database. |
|
</term>
to notify them when the status of
|
a
|
<term>
request
</term>
changes or when a
<term>
|
#877
Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete. |
|
of a
<term>
request
</term>
changes or when
|
a
|
<term>
request
</term>
is complete . We have
|
#882
Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete. |
|
speech recognition
</term>
has brought to light
|
a
|
new problem : as
<term>
dialog systems
</term>
|
#940
However, 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. |
|
word or semantic error rate
</term>
) from
|
a
|
list of
<term>
word strings
</term>
, where
|
#1096
The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
|
string
</term>
has been obtained by using
|
a
|
different
<term>
LM
</term>
. Actually , the
|
#1111
The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
|
Actually , the
<term>
oracle
</term>
acts like
|
a
|
<term>
dynamic combiner
</term>
with
<term>
hard
|
#1121
Actually, the oracle acts like a dynamic combiner with hard decisions using the reference. |
|
experimental results that clearly show the need for
|
a
|
<term>
dynamic language model combination
|
#1141
We provide experimental results that clearly show the need for a dynamic language model combination to improve the performance further. |
|
<term>
performance
</term>
further . We suggest
|
a
|
method that mimics the behavior of the
<term>
|
#1154
We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. |
|
behavior of the
<term>
oracle
</term>
using
|
a
|
<term>
neural network
</term>
or a
<term>
decision
|
#1164
We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. |
|
</term>
using a
<term>
neural network
</term>
or
|
a
|
<term>
decision tree
</term>
. The method amounts
|
#1168
We suggest a method that mimics the behavior of the oracle using a neural network or a decision tree. |
|
best
<term>
confidence
</term>
. We describe
|
a
|
three-tiered approach for
<term>
evaluation
|
#1197
We describe a three-tiered approach for evaluation of spoken dialogue systems. |
|
the U.S. military . This paper proposes
|
a
|
practical approach employing
<term>
n-gram
|
#1244
This paper proposes a practical approach employing n-gram models and error-correction rules for Thai key prediction and Thai-English language identification. |
|
</term>
.
<term>
Sentence planning
</term>
is
|
a
|
set of inter-related but distinct tasks
|
#1296
Sentence 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. |
|
this paper , we present
<term>
SPoT
</term>
,
|
a
|
<term>
sentence planner
</term>
, and a new
|
#1343
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>
, a
<term>
sentence planner
</term>
, and
|
a
|
new methodology for automatically training
|
#1348
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. |
|
task into two distinct phases . First ,
|
a
|
very simple ,
<term>
randomized sentence-plan-generator
|
#1376
First, a very simple, randomized sentence-plan-generator (SPG) generates a potentially large list of possible sentence plans for a given text-plan input. |
|
sentence-plan-generator ( SPG )
</term>
generates
|
a
|
potentially large list of possible
<term>
|
#1386
First, a very simple, randomized sentence-plan-generator (SPG) generates a potentially large list of possible sentence plans for a given text-plan input. |
|
of possible
<term>
sentence plans
</term>
for
|
a
|
given
<term>
text-plan input
</term>
. Second
|
#1395
First, a very simple, randomized sentence-plan-generator (SPG) generates a potentially large list of possible sentence plans for a given text-plan input. |