</term>
and
<term>
reference
</term>
to the structure
#19412We identify three important requirements which arose from the task that we gave our subjects: operators specific to the task of database access,complex contextual reference and reference to the structure of the information source.
other,16-6-E89-1016,ak
the task that we gave our subjects :
<term>
operators
</term>
specific to the task of
<term>
database
#19403We identify three important requirements which arose from the task that we gave our subjects:operators specific to the task of database access, complex contextual reference and reference to the structure of the information source.
other,29-6-E89-1016,ak
complex contextual reference
</term>
and
<term>
reference
</term>
to the structure of the
<term>
information
#19416We identify three important requirements which arose from the task that we gave our subjects: operators specific to the task of database access, complex contextual reference andreference to the structure of the information source.
tech,9-7-E89-1016,ak
these might be satisfied by future
<term>
Natural Language systems
</term>
. Recently , we initiated a project
#19434We discuss how these might be satisfied by futureNatural Language systems.
tech,18-1-E89-1016,ak
used in the
<term>
evaluation
</term>
of
<term>
Natural Language systems
</term>
. We conclude that previous approaches
#19299This paper presents a critical discussion of the various approaches that have been used in the evaluation ofNatural Language systems.
other,22-6-E89-1016,ak
operators
</term>
specific to the task of
<term>
database access
</term>
,
<term>
complex contextual reference
#19409We identify three important requirements which arose from the task that we gave our subjects: operators specific to the task ofdatabase access, complex contextual reference and reference to the structure of the information source.
tech,16-5-E89-1016,ak
technique , place upon a prototype
<term>
Natural Language system
</term>
. We identify three important requirements
#19383We evaluate the demands that task dialogues collected using this technique, place upon a prototypeNatural Language system.
tech,22-2-E89-1016,ak
use , e.g. solving a task requiring
<term>
data retrieval
</term>
. This raises questions about the
#19325We conclude that previous approaches have neglected to evaluate systems in the context of their use, e.g. solving a task requiringdata retrieval.
other,5-5-E89-1016,ak
task . We evaluate the demands that
<term>
task dialogues
</term>
collected using this technique ,
#19372We evaluate the demands thattask dialogues collected using this technique, place upon a prototype Natural Language system.
other,5-3-E89-1016,ak
</term>
. This raises questions about the
<term>
validity
</term>
of such approaches . In the second
#19333This raises questions about thevalidity of such approaches.
tech,16-1-E89-1016,ak
approaches that have been used in the
<term>
evaluation
</term>
of
<term>
Natural Language systems
</term>
#19297This paper presents a critical discussion of the various approaches that have been used in theevaluation of Natural Language systems.
other,35-6-E89-1016,ak
reference
</term>
to the structure of the
<term>
information source
</term>
. We discuss how these might be satisfied
#19422We identify three important requirements which arose from the task that we gave our subjects: operators specific to the task of database access, complex contextual reference and reference to the structure of theinformation source.
tech,15-4-E89-1016,ak
report a laboratory study using the
<term>
Wizard of Oz technique
</term>
to identify NL requirements for carrying
#19353In the second half of the paper, we report a laboratory study using theWizard of Oz technique to identify NL requirements for carrying out this task.