| tech,6-1-A92-1026,bq | </term> . It is often assumed that when <term> | natural language processing | </term> meets the real world , the ideal | #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 | abandoned . However , our experience with <term> | TACITUS | </term> ; especially in the <term> MUC-3 evaluation | #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 | <term> TACITUS </term> ; especially in the <term> | MUC-3 evaluation | </term> , has shown that principled techniques | #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 | shown that principled techniques for <term> | syntactic and pragmatic analysis | </term> can be bolstered with methods for | #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 | describe three techniques for making <term> | syntactic analysis | </term> more robust --- an <term> agenda-based | #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 | analysis </term> more robust --- an <term> | agenda-based scheduling parser | </term> , a <term> recovery technique for failed | #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 | agenda-based scheduling parser </term> , a <term> | recovery technique for failed parses | </term> , and a new technique called <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 | </term> , and a new technique called <term> | terminal substring parsing | </term> . For <term> pragmatics processing </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 | terminal substring parsing </term> . For <term> | pragmatics processing | </term> , we describe how the method of <term> | #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 | </term> , we describe how the method of <term> | abductive inference | </term> is inherently robust , in that an | #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 | 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. |
