Mathematical Modelling of the Pattern of Occurrence of Words in Different Corpora of the Hindi Language.
Hemlata PandeH. S. DhamiPublished in: J. Quant. Linguistics (2013)
Keyphrases
- parallel corpus
- comparable corpora
- indian languages
- text corpora
- word pairs
- source language
- target language
- word order
- statistical machine translation
- linguistic knowledge
- natural language processing
- machine translation
- spoken language
- cross lingual
- computational linguistics
- pattern languages
- lexical information
- human language
- word frequency
- syntactic categories
- pattern matching
- programming language
- language specific
- text documents
- linguistic resources
- cross language information retrieval
- occurrence frequency
- language identification
- natural language
- related words
- n gram
- language learning
- query translation
- text corpus
- word forms
- bilingual dictionaries
- multiword
- word sense disambiguation
- semantic relations
- parallel corpora
- word level
- translation model
- contextual features
- pos taggers
- named entity recognition
- surprising patterns
- occurrence probabilities