A comparative study of syllables and character level N-grams for Dravidian multi-script and code-mixed offensive language identification.
Fazlourrahman BalouchzahiHosahalli Lakshmaiah ShashirekhaGrigori SidorovAlexander F. GelbukhPublished in: J. Intell. Fuzzy Syst. (2022)
Keyphrases
- language identification
- n gram
- language model
- document images
- speaker identification
- variable length
- speech recognition
- bag of words
- word level
- text classification
- language modeling
- language independent
- text lines
- indian languages
- machine vision
- character n grams
- optical character recognition
- machine learning
- natural language processing
- probabilistic model
- natural language
- pattern recognition