Page: 1... 62 63 64 65 66 67 68 69 70... 82
Hits 1.301 – 1.320 of 1.629
1301 |
Tipster Shogun System (Joint GE-CMU): MUC-4 Test Results and Analysis
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
1302 |
GE-CMU: Description of the Tipster/Shogun System as Used for MUC-4
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
1303 |
BBN PLUM: MUC-4 Test Results and Analysis
|
|
|
|
In: DTIC (1992)
|
|
BASE
|
|
Show details
|
|
1304 |
Development of a Spoken Language System
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
1306 |
Overview of the Fourth Message Understanding Evaluation and Conference
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
1307 |
VHDL and Waves Descriptions for a Pseudo-Random Pattern Generator
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
1308 |
An Evaluation Methodology for Natural Language Processing Systems
|
|
|
|
In: DTIC AND NTIS (1992)
|
|
BASE
|
|
Show details
|
|
1309 |
Dialect intelligibility testing among Central Yambasa speech varieties
|
|
|
|
BASE
|
|
Show details
|
|
1316 |
Robust Processing of Real-World Natural-Language Texts
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
Abstract:
It is often assumed that when natural language processing meets the real world, the ideal of aiming for complete and correct interpretations has to be abandoned. However, 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 achieving robustness. We describe and evaluate a method for dealing with unknown words and a method for filtering out sentences irrelevant to the task. 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 called terminal substring parsing. 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 required world knowledge, performance degrades gracefully. Each of these techniques have been evaluated and the results of the evaluations are presented.
|
|
Keyword:
*NATURAL LANGUAGE; *PARSERS; AIMING; FILTRATION; LANGUAGE; Linguistics; PROCESSING; RECOVERY; SCHEDULING; TERMINALS; TEST PROCESSING
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA258837 http://www.dtic.mil/docs/citations/ADA258837
|
|
BASE
|
|
Hide details
|
|
1317 |
BBN HARC and DELPHI Results on the ATIS Benchmarks - February 1991
|
|
|
|
In: DTIC (1991)
|
|
BASE
|
|
Show details
|
|
1320 |
Very High Speed Integrated Circuits (VHSIC) Hardware Description Language (VHDL) Syntax and Semantics Summary
|
|
|
|
In: DTIC AND NTIS (1991)
|
|
BASE
|
|
Show details
|
|
Page: 1... 62 63 64 65 66 67 68 69 70... 82
|
|