Arabic/English word translation disambiguation approach based on naive Bayesian classifier.
Farag AhmedAndreas NürnbergerPublished in: IMCSIT (2008)
Keyphrases
- naive bayesian classifier
- cross language information retrieval
- bilingual dictionaries
- arabic documents
- query translation
- machine translation
- character n grams
- translation model
- english chinese
- statistical machine translation
- word sense disambiguation
- machine translation system
- parallel corpus
- target word
- naive bayes
- word sense
- unknown words
- sense disambiguation
- source language
- bayesian classifier
- cross language
- cross lingual
- parallel corpora
- word spotting
- chinese english
- target language
- multiword
- english words
- n gram
- language identification
- arabic language
- out of vocabulary
- natural language processing
- wordnet
- word level
- co occurrence
- word alignment
- natural language
- highly ambiguous
- training corpus
- information extraction
- english text
- question answering
- part of speech
- decision trees
- classification accuracy
- feature selection
- machine learning
- handwritten words
- data sets
- language specific
- sentence pairs
- text classification
- compound words
- data mining