Simultaneous Domain Adaptation of Tokenization and Machine Translation.
Taisei EnomotoTosho HirasawaHwichan KimTeruaki OkaMamoru KomachiPublished in: PACLIC (2023)
Keyphrases
- domain adaptation
- machine translation
- pos tagging
- semi supervised
- natural language processing
- language independent
- cross domain
- cross lingual
- target language
- named entities
- information extraction
- natural language
- labeled data
- sentiment classification
- semi supervised learning
- test data
- multiple sources
- cross language information retrieval
- statistical machine translation
- unlabeled data
- target domain
- machine translation system
- document classification
- co training
- word sense disambiguation
- transfer learning
- query translation
- text categorization
- knowledge discovery
- active learning