Multifractal analysis of sentence lengths in English literary texts
Iwona Grabska-GradzinskaAndrzej KuligJaroslaw KwapienPawel OswiecimkaStanislaw DrozdzPublished in: CoRR (2012)
Keyphrases
- natural language
- multifractal analysis
- training corpus
- linguistic features
- brazilian portuguese
- discourse structure
- natural language generation
- syntactic analysis
- microarray
- parallel corpus
- native language
- parse tree
- linguistic analysis
- part of speech
- text classification
- text generation
- english words
- machine translation
- natural language text
- english language
- syntactic structures
- sentence pairs
- text corpus
- target language
- machine learning
- word level
- arabic language
- word order
- semantic roles
- natural language processing
- statistical machine translation
- stop words
- sentence level
- english text
- source language
- word sense
- text analysis
- information extraction
- domain dependent
- language learning
- text documents