KWPSI - an algorithmically derived Key Word/Phrase Subject Index
Description
A new type of algorithmically derived subject index, called Key Word/Phrase Subject Index (KWPSI) has been developed. The KWPSI is based on noun phrase entries algorithmically derived from titles. The procedure employs approximate syntactic and semantic analysis resulting in multilevel substring analyses of titles. The generation of subject entries from the analyzed titles is performed then by use of a small number of transformational rules. KWPSI's structure and appearance are similar to the traditional three-level hierarchic structure of intellectually compiled subject indexes (main heading followed by one or more modifying phrases) with an additional feature believed to enhance its browsability. The display of KWPSI-type Key Word/Phrase vocabularies to facilitate on-line searching in a new multilevel mode is suggested. 6 figures
Additional details
Publishing Information
- Journal Title
- Proc. ASIS Annu. Meet.
- Journal Volume
- 16
- Series
- Proc. ASIS Annu. Meet.
- Journal Page Range
- 236-245
Conference
- Title
- 42. annual meeting of the American Society for Information Science.
- Dates
- 14 - 18 Oct 1979.
- Place
- Minneapolis, MN, USA.
INIS
- Country of Publication
- United States
- Country of Input or Organization
- United States
- INIS RN
- 12582602
- Subject category
- S99: GENERAL AND MISCELLANEOUS;
- Resource subtype / Literary indicator
- Conference
- Descriptors DEI
- ALGORITHMS; AUTOMATION; INFORMATION RETRIEVAL; INFORMATION SYSTEMS
Optional Information
- Secondary number(s)
- CONF-7910144--.