Login / Signup
Quantifying the impact of dirty OCR on historical text analysis: Eighteenth Century Collections Online as a case study.
Mark J. Hill
Simon Hengchen
Published in:
Digit. Scholarsh. Humanit. (2019)
Keyphrases
</>
text analysis
text collections
text mining
text documents
natural language processing
information extraction
optical character recognition
metadata
databases
character recognition
document images
multi dimensional
text categorization
digital libraries
textual data
multiscale
artificial intelligence