#22444We describe three techniques for making syntactic analysis more robust---an agenda-based scheduling parser, arecovery technique for failed parses, and a new technique called terminal substring parsing.
other,30-2-A92-1026,ak
bolstered with methods for achieving
<term>
robustness
</term>
. We describe three techniques for
#22425However, our experience with TACITUS; especially in the MUC-3 evaluation, has shown that principled techniques for syntactic and pragmatic analysis can be bolstered with methods for achievingrobustness.
tech,12-3-A92-1026,ak
analysis
</term>
more robust --- an
<term>
agenda-based scheduling parser
</term>
, a
<term>
recovery technique
</term>
#22439We describe three techniques for making syntactic analysis more robust---anagenda-based scheduling parser, a recovery technique for failed parses, and a new technique called terminal substring parsing.
other,19-4-A92-1026,ak
</term>
is inherently robust , in that an
<term>
interpretation
</term>
is always possible , so that in the
#22478For pragmatics processing, we describe how the method of abductive inference is inherently robust, in that aninterpretation is always possible, so that in the absence of the required world knowledge, performance degrades gracefully.
tech,28-3-A92-1026,ak
</term>
, and a new technique called
<term>
terminal substring parsing
</term>
. For
<term>
pragmatics processing
</term>
#22455We describe three techniques for making syntactic analysis more robust---an agenda-based scheduling parser, a recovery technique for failed parses, and a new technique calledterminal substring parsing.
other,22-1-A92-1026,ak
of aiming for complete and correct
<term>
interpretations
</term>
has to be abandoned . However , our
#22389It is often assumed that when natural language processing meets the real world, the ideal of aiming for complete and correctinterpretations has to be abandoned.
other,21-3-A92-1026,ak
recovery technique
</term>
for failed
<term>
parses
</term>
, and a new technique called
<term>
#22448We describe three techniques for making syntactic analysis more robust---an agenda-based scheduling parser, a recovery technique for failedparses, and a new technique called terminal substring parsing.
tech,1-4-A92-1026,ak
terminal substring parsing
</term>
. For
<term>
pragmatics processing
</term>
, we describe how the method of
<term>
#22460Forpragmatics processing, we describe how the method of abductive inference is inherently robust, in that an interpretation is always possible, so that in the absence of the required world knowledge, performance degrades gracefully.
tech,19-2-A92-1026,ak
shown that principled techniques for
<term>
syntactic and pragmatic analysis
</term>
can be bolstered with methods for
#22414However, our experience with TACITUS; especially in the MUC-3 evaluation, has shown that principled techniques forsyntactic and pragmatic analysis can be bolstered with methods for achieving robustness.
tech,6-3-A92-1026,ak
describe three techniques for making
<term>
syntactic analysis
</term>
more robust --- an
<term>
agenda-based
#22433We describe three techniques for makingsyntactic analysis more robust---an agenda-based scheduling parser, a recovery technique for failed parses, and a new technique called terminal substring parsing.
tech,10-4-A92-1026,ak
</term>
, we describe how the method of
<term>
abductive inference
</term>
is inherently robust , in that an
#22469For pragmatics processing, we describe how the method ofabductive inference is inherently robust, in that an interpretation is always possible, so that in the absence of the required world knowledge, performance degrades gracefully.
other,32-4-A92-1026,ak
that in the absence of the required
<term>
world knowledge
</term>
, performance degrades gracefully
#22491For pragmatics processing, we describe how the method of abductive inference is inherently robust, in that an interpretation is always possible, so that in the absence of the requiredworld knowledge, performance degrades gracefully.
other,10-2-A92-1026,ak
<term>
TACITUS
</term>
; especially in the
<term>
MUC-3 evaluation
</term>
, has shown that principled techniques
#22405However, our experience with TACITUS; especially in theMUC-3 evaluation, has shown that principled techniques for syntactic and pragmatic analysis can be bolstered with methods for achieving robustness.
tech,6-1-A92-1026,ak
</term>
. It is often assumed that when
<term>
natural language processing
</term>
meets the real world , the ideal
#22373It is often assumed that whennatural language processing meets the real world, the ideal of aiming for complete and correct interpretations has to be abandoned.
tool,5-2-A92-1026,ak
abandoned . However , our experience with
<term>
TACITUS
</term>
; especially in the
<term>
MUC-3 evaluation
#22400However, our experience withTACITUS; especially in the MUC-3 evaluation, has shown that principled techniques for syntactic and pragmatic analysis can be bolstered with methods for achieving robustness.