Negative filter
Error, correction 12
(384.2 per million)
tech,3-1-J86-1002,ak
multi-lingual texts
</term>
. A method for
<term>
error correction
</term>
of
<term>
ill-formed input
</term>
is
#16174A method forerror correction of ill-formed input is described that acquires dialogue patterns in typical usage and uses these patterns to predict new inputs.
other,6-1-J86-1002,ak
for
<term>
error correction
</term>
of
<term>
ill-formed input
</term>
is described that acquires
<term>
dialogue
#16177A method for error correction ofill-formed input is described that acquires dialogue patterns in typical usage and uses these patterns to predict new inputs.
model,12-1-J86-1002,ak
input
</term>
is described that acquires
<term>
dialogue patterns
</term>
in typical usage and uses these
<term>
#16183A method for error correction of ill-formed input is described that acquiresdialogue patterns in typical usage and uses these patterns to predict new inputs.
model,20-1-J86-1002,ak
</term>
in typical usage and uses these
<term>
patterns
</term>
to predict new
<term>
inputs
</term>
#16191A method for error correction of ill-formed input is described that acquires dialogue patterns in typical usage and uses thesepatterns to predict new inputs.
other,24-1-J86-1002,ak
<term>
patterns
</term>
to predict new
<term>
inputs
</term>
.
<term>
Error correction
</term>
is
#16195A method for error correction of ill-formed input is described that acquires dialogue patterns in typical usage and uses these patterns to predict newinputs.
tech,7-2-J86-1002,ak
</term>
is done by strongly biasing
<term>
parsing
</term>
toward
<term>
expected meanings
</term>
#16204Error correction is done by strongly biasingparsing toward expected meanings unless clear evidence from the input shows the current sentence is not expected.
other,9-2-J86-1002,ak
biasing
<term>
parsing
</term>
toward
<term>
expected meanings
</term>
unless clear evidence from the
<term>
#16206Error correction is done by strongly biasing parsing towardexpected meanings unless clear evidence from the input shows the current sentence is not expected.
other,16-2-J86-1002,ak
</term>
unless clear evidence from the
<term>
input
</term>
shows the current
<term>
sentence
</term>
#16213Error correction is done by strongly biasing parsing toward expected meanings unless clear evidence from theinput shows the current sentence is not expected.
other,20-2-J86-1002,ak
<term>
input
</term>
shows the current
<term>
sentence
</term>
is not expected . A
<term>
dialogue
#16217Error correction is done by strongly biasing parsing toward expected meanings unless clear evidence from the input shows the currentsentence is not expected.
tech,1-3-J86-1002,ak
sentence
</term>
is not expected . A
<term>
dialogue acquisition and tracking algorithm
</term>
is presented along with a description
#16223Adialogue acquisition and tracking algorithm is presented along with a description of its implementation in a voice interactive system.
tech,17-3-J86-1002,ak
description of its implementation in a
<term>
voice interactive system
</term>
. A series of tests are described
#16239A dialogue acquisition and tracking algorithm is presented along with a description of its implementation in avoice interactive system.
tech,12-4-J86-1002,ak
described that show the power of the
<term>
error correction methodology
</term>
when stereotypic
<term>
dialogue
</term>
#16255A series of tests are described that show the power of theerror correction methodology when stereotypic dialogue occurs.