Vartani Spellcheck - Automatic Context-Sensitive Spelling Correction of OCR-generated Hindi Text Using BERT and Levenshtein Distance.
Aditya PalAbhijit MustafiPublished in: CoRR (2020)
Keyphrases
- spelling correction
- context sensitive
- optical character recognition
- english text
- levenshtein distance
- language identification
- document images
- information retrieval
- multiword
- character recognition
- text mining
- edit distance
- document analysis
- natural language
- language model
- text documents
- machine translation
- semantic information
- keywords
- clustering algorithm
- data analysis