Improving Sampling-based Alignment by Investigating the Distribution of N-grams in Phrase Translation Tables.
Juan LuoAdrien LardilleuxYves LepagePublished in: PACLIC (2011)
Keyphrases
- n gram
- word level
- language independent
- language model
- text classification
- language modelling
- machine translation
- word segmentation
- bag of words
- variable length
- part of speech
- word alignment
- viterbi algorithm
- language modeling
- character n grams
- databases
- translation model
- co occurrence
- keywords
- web documents
- statistical machine translation
- machine translation system
- image representation
- text mining
- out of vocabulary
- artificial intelligence