Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation.
Di WuChristof MonzPublished in: CoRR (2023)
Keyphrases
- machine translation
- language specific
- cross lingual
- language independent
- target language
- out of vocabulary
- machine translation system
- statistical machine translation
- multilingual documents
- parallel corpus
- cross language information retrieval
- word sense disambiguation
- cross lingual information retrieval
- language resources
- word level
- bilingual dictionaries
- parallel corpora
- natural language processing
- word segmentation
- chinese english
- language processing
- translation model
- natural language
- source language
- word alignment
- indian languages
- query translation
- information extraction
- comparable corpora
- natural language generation
- n gram
- machine readable dictionaries
- keywords
- english chinese
- tasks in natural language processing
- co occurrence
- word order
- cross language
- sentiment classification
- word pairs