A semi-automatic approach to identifying and unifying ambiguously encoded Arabic-based characters.
Sardar F. JafPublished in: IALP (2016)
Keyphrases
- semi automatic
- fully automatic
- optical character recognition
- gold standard
- printed documents
- ontology mapping
- domain ontology
- semi automatically
- wrapper generation
- ontology development
- labor intensive
- arabic language
- writer identification
- manual annotation
- handwritten words
- information retrieval
- landmark extraction
- design rationale
- ontology engineering
- semantic annotation
- information retrieval systems
- co occurrence
- natural language processing