A novel approach to the extraction of roots from Arabic words using bigrams.
Ismail HmeidiRiyad Al-ShalabiAhmad T. Al-TaaniHassan NajadatShaker A. Al-HazaimehPublished in: J. Assoc. Inf. Sci. Technol. (2010)
Keyphrases
- n gram
- arabic language
- unknown words
- arabic text
- language model
- arabic documents
- word segmentation
- training corpus
- keywords
- part of speech
- printed text
- information retrieval
- handwritten documents
- related words
- word recognition
- automatic extraction
- morphological analysis
- word sense disambiguation
- information extraction
- automatically extracting
- multiword
- text recognition
- word spotting
- text retrieval
- speech corpus