Domain Adaptation in MT Using Titles in Wikipedia as a Parallel Corpus: Resources and Evaluation.
Gorka LabakaIñaki AlegriaKepa SarasolaPublished in: LREC (2016)
Keyphrases
- domain adaptation
- machine translation
- parallel corpus
- concept space
- cross lingual
- cross domain
- labeled data
- semi supervised learning
- multiple sources
- query translation
- parallel corpora
- sentiment classification
- language independent
- information extraction
- wikipedia articles
- cross language information retrieval
- unlabeled data
- semi supervised
- target domain
- target language
- training data
- statistical machine translation