Comparing source and target texts in a translation corpus.
Magnus MerkelPublished in: NODALIDA (2001)
Keyphrases
- training corpus
- english words
- statistical machine translation
- newspaper articles
- target language
- parallel corpora
- translation model
- machine translation system
- text corpus
- natural language text
- linguistic information
- machine translation
- scientific papers
- cross language information retrieval
- world knowledge
- parallel corpus
- source language
- text mining
- genia corpus
- keywords
- manually annotated
- target tracking
- text classification
- target object
- text documents
- syntactic analysis
- linguistic patterns
- information extraction systems
- text categorization
- chinese english
- test set
- word pairs
- word alignment
- part of speech
- query translation
- word sense
- natural language generation