An n-gram Approach to Exploiting a Monolingual Corpus for Machine Translation.
Toni BadiaGemma BoledaMaite MeleroAntoni OliverPublished in: MTSummit (Workshop) (2005)
Keyphrases
- n gram
- machine translation
- statistical machine translation
- parallel corpus
- language independent
- machine translation system
- chinese english
- language model
- language specific
- cross lingual
- parallel corpora
- word alignment
- language modeling
- out of vocabulary
- information extraction
- cross language information retrieval
- bag of words
- text classification
- finite state transducers
- natural language processing
- target language
- word level
- viterbi algorithm
- word sense disambiguation
- source language
- part of speech
- word segmentation
- query translation
- tasks in natural language processing
- natural language
- information retrieval
- bilingual dictionaries
- cross language
- document retrieval
- test collection
- web documents
- character n grams