A context-based approach to text recognition
Technical Report
·
OSTI ID:68578
- Nottingham Trent Univ., Nottingham (United Kingdom)
The performance of text recognition systems may be improved by applying higher-level knowledge in the form of contextual information. However, the acquisition of such information for a realistically sized vocabulary presents a major problem, since hand-coding is feasible for only the smallest of vocabularies. This paper describes a number of methods for extracting contextual knowledge from text corpora, and compares the effect of each on the performance of text recognition systems.
- Research Organization:
- Nevada Univ., Las Vegas, NV (United States)
- OSTI ID:
- 68578
- Report Number(s):
- CONF-9404212-; TRN: 95:004349-0018
- Resource Relation:
- Conference: 3. annual symposium on document analysis and information retrieval, Las Vegas, NV (United States), 11-13 Apr 1994; Other Information: PBD: 1994; Related Information: Is Part Of Third Annual Symposium on Document Analysis and Information Retrieval; PB: 484 p.
- Country of Publication:
- United States
- Language:
- English
Similar Records
Automatic generation, validation and utilization of a knowledge-base: An artificial neural network approach
Information Extraction from Unstructured Text for the Biodefense Knowledge Center
Lexicon-based word recognition without word segmentation
Miscellaneous
·
Sun Jan 01 00:00:00 EST 1989
·
OSTI ID:68578
Information Extraction from Unstructured Text for the Biodefense Knowledge Center
Conference
·
Fri Apr 29 00:00:00 EDT 2005
·
OSTI ID:68578
+6 more
Lexicon-based word recognition without word segmentation
Technical Report
·
Sat Dec 31 00:00:00 EST 1994
·
OSTI ID:68578