Smooth Bilingual N-Gram Translation.
Holger SchwenkMarta R. Costa-jussàJosé A. R. FonollosaPublished in: EMNLP-CoNLL (2007)
Keyphrases
- n gram
- parallel corpora
- language independent
- machine translation
- chinese english
- language model
- character n grams
- out of vocabulary
- cross language information retrieval
- translation model
- statistical machine translation
- query translation
- parallel corpus
- language modeling
- comparable corpora
- word alignment
- machine translation system
- cross lingual
- cross language
- language resources
- bilingual dictionaries
- part of speech
- text classification
- variable length
- source language
- language modelling
- word level
- query expansion
- document retrieval
- viterbi algorithm
- target language
- finite state transducers
- inside outside algorithm
- word segmentation
- multiword
- labor intensive
- wordnet
- information retrieval
- language specific
- machine learning
- text mining