Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation.
Neha VermaKenton MurrayKevin DuhPublished in: AMTA (2022)
Keyphrases
- machine translation
- cross lingual
- domain specific
- language independent
- cross language information retrieval
- language resources
- chinese english
- language specific
- multilingual documents
- machine translation system
- natural language processing
- parallel corpus
- comparable corpora
- natural language generation
- cross lingual information retrieval
- natural language
- query translation
- cross language
- statistical machine translation
- parallel corpora
- multilingual information retrieval
- word alignment
- target language
- information extraction
- language processing
- digital libraries
- artificial intelligence
- bilingual dictionaries
- relation extraction
- word sense disambiguation
- brazilian portuguese
- word level
- word segmentation
- n gram
- text mining