| Title: |
Information from Natural-Language Text |
| Authors: |
John S. Bear; Computer Scientist; W. Mabry Tyson; Computer Facility; David Israel; Mabry Tyson |
| Contributors: |
The Pennsylvania State University CiteSeerX Archives |
| Source: |
http://www.dtic.mil/dtic/tr/fulltext/u2/a259435.pdf. |
| Publication Year: |
1992 |
| Collection: |
CiteSeerX |
| Description: |
FASTUS is a system for extracting information from free text in En-glish, and potentially other languages as well, for entry into a database, and potentially for other applications. It works essentially as a cas- Accesion For caded, nondeterministic finite state automaton. There are four steps NTIS CRAM in the operation of FASTUS. In Step 1 sentences are scanned for cer- N T A&! tain trigger words to determine whether further processing should be DUC T•.3 done. In Step 2 noun groups, verb groups, and prepositions and some Ulai ou;i ed other particles are recognized. The input to Step 3 is the sequence of ___tt__a ____ phrases recognized in Step 2; patterns of interest are identified in Step 3 and corresponding "incident structures " are built up. In Step 4 in- By. cident structures that derive from the same incident are identified and Oist ibution I merged, and these are used in generating database entries. FASTUS is an order of magnitude faster than any comparable system; it can Av.'-, L'C:'.c' |
| Document Type: |
text |
| File Description: |
application/pdf |
| Language: |
English |
| Relation: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.9933; http://www.dtic.mil/dtic/tr/fulltext/u2/a259435.pdf |
| Availability: |
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.9933; http://www.dtic.mil/dtic/tr/fulltext/u2/a259435.pdf |
| Rights: |
Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Accession Number: |
edsbas.AF2CF492 |
| Database: |
BASE |