Keyphrases
- link grammar
- statistical machine translation
- person names
- open domain
- parallel corpus
- broad coverage
- wide coverage
- english words
- english language
- penn treebank
- sentence pairs
- natural language
- training corpus
- multiword
- linguistic features
- word sense
- machine translation
- semantic roles
- machine translation system
- unknown words
- manually annotated
- mono lingual
- parallel corpora
- text classification
- information retrieval
- test set
- stop words
- cross language
- dependency parsing
- english text
- spoken language
- answer questions
- comparable corpora
- cross language information retrieval
- language model
- information extraction
- lexical units