Bi-text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation.
Fahad Al-ObaidliStephen CoxPreslav NakovPublished in: CICLing (2) (2016)
Keyphrases
- statistical machine translation
- word alignment
- arabic language
- grammar induction
- machine translation system
- word level
- machine translation
- phrase based smt
- training corpus
- parallel texts
- multiword
- language model
- translation model
- chinese english
- cross lingual
- source language
- text mining
- language independent
- language processing
- parallel corpus
- cross language information retrieval
- text retrieval
- document images
- minimum error rate
- parallel corpora
- keywords
- document analysis
- semantic information
- speech recognition
- natural language processing
- information retrieval
- target language
- cross language
- text data
- character recognition