Using N-gram and Word Network Features for Native Language Identification.
Shibamouli LahiriRada MihalceaPublished in: BEA@NAACL-HLT (2013)
Keyphrases
- n gram
- language identification
- language independent
- language model
- text classification
- word segmentation
- language modeling
- bag of words
- character n grams
- variable length
- feature extraction
- feature set
- word level
- classification accuracy
- low level
- web documents
- hough transform
- document images
- feature space
- keywords
- machine learning