Actions for Machine aided indexing from natural language text

Email RIS file
Bookmark
Report an Issue

Machine aided indexing from natural language text

Author
Silvester, June P.
Published
Mar 1, 1993.
Physical Description
1 electronic document
Additional Creators
Klingbiel, Paul H. and Genuardi, Michael T.
Online Version

Availability

I Want It
I Want It

Finding items...

Restrictions on Access
Unclassified, Unlimited, Publicly available.
Free-to-read Unrestricted online access
Summary
The NASA Lexical Dictionary (NLD) Machine Aided Indexing (MAI) system was designed to (1) reuse the indexing of the Defense Technical Information Center (DTIC); (2) reuse the indexing of the Department of Energy (DOE); and (3) reduce the time required for original indexing. This was done by automatically generating appropriate NASA thesaurus terms from either the other agency's index terms, or, for original indexing, from document titles and abstracts. The NASA STI Program staff devised two different ways to generate thesaurus terms from text. The first group of programs identified noun phrases by a parsing method that allowed for conjunctions and certain prepositions, on the assumption that indexable concepts are found in such phrases. Results were not always satisfactory, and it was noted that indexable concepts often occurred outside of noun phrases. The first method also proved to be too slow for the ultimate goal of interactive (online) MAI. The second group of programs used the knowledge base (KB), word proximity, and frequency of word and phrase occurrence to identify indexable concepts. Both methods are described and illustrated. Online MAI has been achieved, as well as several spinoff benefits, which are also described.
Other Subject(s)
Collection
NASA Technical Reports Server (NTRS) Collection.
Note
Document ID: 19930017712.
Accession ID: 93N26901.
NAS 1.26:4512.
NASA-CR-4512.
Terms of Use and Reproduction
No Copyright.
View MARC record | catkey: 15670125