Source-Side Suffix Stripping for Bengali-to-English SMT.
Rejwanul HaqueSergio PenkaleJie JiangAndy WayPublished in: IALP (2012)
Keyphrases
- statistical machine translation
- machine translation
- target language
- source language
- word alignment
- machine translation system
- phrase based smt
- training corpus
- language model
- cross lingual
- chinese english
- cross language
- parallel corpora
- cross language information retrieval
- multiword
- suffix tree
- indian languages
- translation model
- natural language
- information retrieval systems
- computer assisted language learning
- multiple sources
- language learning
- data exchange