Named Entity Disambiguation and Linking Historic Newspaper OCR with BERT.
Kai LabuschClemens NeudeckerPublished in: CLEF (Working Notes) (2020)
Keyphrases
- named entity disambiguation
- optical character recognition
- named entities
- post processing
- error correction
- character recognition
- named entity recognition
- preprocessing
- document images
- cultural heritage
- information extraction
- recognition errors
- text recognition
- document processing
- printed documents
- machine learning
- knowledge base
- active learning
- relation extraction