tech,6-1-A92-1026,bq |
It is often assumed that when
<term>
natural language processing
</term>
meets the real world , the ideal of aiming for complete and correct interpretations has to be abandoned .
|
#17402
It 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,bq |
However , our experience with
<term>
TACITUS
</term>
; especially in the
<term>
MUC-3 evaluation
</term>
, has shown that principled techniques for
<term>
syntactic and pragmatic analysis
</term>
can be bolstered with methods for achieving robustness .
|
#17429
However, 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. |
other,10-2-A92-1026,bq |
However , our experience with
<term>
TACITUS
</term>
; especially in the
<term>
MUC-3 evaluation
</term>
, has shown that principled techniques for
<term>
syntactic and pragmatic analysis
</term>
can be bolstered with methods for achieving robustness .
|
#17434
However, 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,19-2-A92-1026,bq |
However , our experience with
<term>
TACITUS
</term>
; especially in the
<term>
MUC-3 evaluation
</term>
, has shown that principled techniques for
<term>
syntactic and pragmatic analysis
</term>
can be bolstered with methods for achieving robustness .
|
#17443
However, 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,bq |
We describe three techniques for making
<term>
syntactic analysis
</term>
more robust --- an
<term>
agenda-based scheduling parser
</term>
, a
<term>
recovery technique for failed parses
</term>
, and a new technique called
<term>
terminal substring parsing
</term>
.
|
#17462
We 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,12-3-A92-1026,bq |
We describe three techniques for making
<term>
syntactic analysis
</term>
more robust --- an
<term>
agenda-based scheduling parser
</term>
, a
<term>
recovery technique for failed parses
</term>
, and a new technique called
<term>
terminal substring parsing
</term>
.
|
#17468
We 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. |
tech,17-3-A92-1026,bq |
We describe three techniques for making
<term>
syntactic analysis
</term>
more robust --- an
<term>
agenda-based scheduling parser
</term>
, a
<term>
recovery technique for failed parses
</term>
, and a new technique called
<term>
terminal substring parsing
</term>
.
|
#17473
We 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. |
tech,28-3-A92-1026,bq |
We describe three techniques for making
<term>
syntactic analysis
</term>
more robust --- an
<term>
agenda-based scheduling parser
</term>
, a
<term>
recovery technique for failed parses
</term>
, and a new technique called
<term>
terminal substring parsing
</term>
.
|
#17484
We 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. |
tech,1-4-A92-1026,bq |
For
<term>
pragmatics processing
</term>
, we describe how the method of
<term>
abductive inference
</term>
is inherently robust , in that an interpretation is always possible , so that in the absence of the required
<term>
world knowledge
</term>
, performance degrades gracefully .
|
#17489
Forpragmatics 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,10-4-A92-1026,bq |
For
<term>
pragmatics processing
</term>
, we describe how the method of
<term>
abductive inference
</term>
is inherently robust , in that an interpretation is always possible , so that in the absence of the required
<term>
world knowledge
</term>
, performance degrades gracefully .
|
#17498
For 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,bq |
For
<term>
pragmatics processing
</term>
, we describe how the method of
<term>
abductive inference
</term>
is inherently robust , in that an interpretation is always possible , so that in the absence of the required
<term>
world knowledge
</term>
, performance degrades gracefully .
|
#17520
For 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. |