A Corpus Based Technique for Repairing Ill-formed Sentences with Word Order Errors Using Co-Occurrences of n-Grams.
Theologos AthanaselisKonstantinos MamourasStelios BakamidisIoannis DologlouPublished in: Int. J. Artif. Intell. Tools (2011)
Keyphrases
- co occurrence
- n gram
- word order
- bag of words
- language model
- target language
- text classification
- word sense
- natural language generation
- language independent
- document representation
- language modeling
- wordnet
- semantic similarity
- part of speech
- semantic relations
- natural language
- text documents
- word segmentation
- named entities
- topic models
- action recognition
- latent semantic indexing
- image classification
- sentence level
- machine learning
- test collection
- knn