Overview of the 2017 ALTA Shared Task: Correcting OCR Errors.
Diego Mollá AliodSteve CassidyPublished in: ALTA (2017)
Keyphrases
- recognition errors
- optical character recognition
- character recognition
- error correction
- test set
- document images
- post processing
- automatic speech recognition
- page layout
- document processing
- error detection
- coreference resolution
- genetic algorithm
- document image analysis
- preprocessing
- text recognition
- natural language
- information systems