On lexical resources for digitization of historical documents.
Annette GotscharekUlrich ReffleChristoph RinglstetterKlaus U. SchulzPublished in: ACM Symposium on Document Engineering (2009)
Keyphrases
- historical documents
- lexical resources
- wordnet
- handwriting recognition
- natural language processing
- opinion mining
- ontology learning
- word recognition
- document images
- semantic technologies
- word sense disambiguation
- semantic representations
- computational linguistics
- domain ontology
- co occurrence
- character recognition
- sentiment analysis
- semantic information
- word segmentation
- semi automatic
- sentiment classification
- speech recognition
- visual features
- knowledge base
- handwritten documents
- semantic relations
- information extraction
- probabilistic model