Using Large N-gram for Vietnamese Spell Checking.
Nguyen Thi Xuan HuongTran-Thai DangThe-Tung NguyenAnh-Cuong LePublished in: KSE (2014)
Keyphrases
- n gram
- language model
- bag of words
- text classification
- language modeling
- language modelling
- part of speech
- variable length
- word segmentation
- language independent
- viterbi algorithm
- document representation
- named entity recognition
- web documents
- inside outside algorithm
- character n grams
- machine learning
- natural language processing
- information retrieval