Using a Large Monolingual Corpus to Improve Translation Accuracy.
Radu SoricutKevin KnightDaniel MarcuPublished in: AMTA (2002)
Keyphrases
- statistical machine translation
- machine translation
- machine translation system
- parallel corpus
- query translation
- cross language information retrieval
- question answering
- information retrieval
- cross language
- classification accuracy
- chinese english
- computational cost
- word alignment
- high accuracy
- parallel corpora
- text mining
- parallel texts
- cross language retrieval
- pos tagging
- bilingual dictionaries
- target language
- language model
- query expansion
- error rate
- translation model
- domain specific
- machine learning
- cross lingual
- prediction accuracy