Natural Language Text Retrieval Using a Large Semantic Network

reportActive / Technical Report | Accession Number: ADA274319 | Open PDF

Abstract:

The primary objective of this SBIR effort is to explore and demonstrate advanced performance in precision and recall for text retrieval software. Advanced performance will be accomplished by using dictionaries specifically WordNet from Princeton University and other enhancements to the base technology of ConQuest improved ranking, syntactic processing, etc. Demonstration of accuracy will be performed as a series of retrieval experiments and tests, using the TREC-2 corpus and queries.

Author(s):
Nelson, Paul
Author Organization(s):
CONQUEST SOFTWARE INC COLUMBIA MD
Descriptive Note:
Final rept.
Supplementary Note:
DOI: 10.21236/ADA274319
Pagination:
0047

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Contract/Grant Number(s):
DAAH01-93-C-R201, ARPA ORDER-5916
Monitor Series:
USAMICOM
 Subject Terms
Joint Capability Areas:
JCA_5_Command and Control; JCA_5.3_Planning; JCA_1.2.6_Concepts; JCA_1.3.1_Personnel and Family Support; JCA_5.5.2_Task; JCA_5.5_Direct; JCA_1.2.7_Experimentation
Modernization Areas:
Fully Networked C3; AI and Machine Learning
Communities of Interest:
C4I
Descriptor(s):
*INFORMATION RETRIEVAL, *NATURAL LANGUAGE, *TEXT PROCESSING, SOFTWARE ENGINEERING, DICTIONARIES, SEMANTICS
Field(s)/Group(s):
Linguistics, Computer Programming and Software
Keyword(s):
SBIR
Report Date:
1993 Dec 20