Improving Alignment for SMT by Reordering and Augmenting the Training Corpus.
Maria HolmqvistSara StymneJody FooLars AhrenbergPublished in: WMT@EACL (2009)
Keyphrases
- training corpus
- statistical machine translation
- word alignment
- text classification
- machine translation
- translation model
- language model
- training data
- part of speech
- machine translation system
- cross lingual
- parallel corpora
- cross language information retrieval
- topic models
- question answering
- query expansion
- knowledge discovery
- data analysis