Disentangling Pretrained Representation to Leverage Low-Resource Languages in Multilingual Machine Translation.
Frederikus HudiZhi QuHidetaka KamigaitoTaro WatanabePublished in: LREC/COLING (2024)
Keyphrases
- machine translation
- cross lingual
- language independent
- language resources
- multilingual documents
- language specific
- target language
- machine translation system
- multilingual information retrieval
- cross language information retrieval
- cross lingual information retrieval
- comparable corpora
- information extraction
- statistical machine translation
- parallel corpus
- chinese english
- word sense disambiguation
- cross language
- parallel corpora
- natural language processing
- natural language generation
- natural language
- source language
- word alignment
- query translation
- word level
- bilingual dictionaries
- text retrieval
- text classification
- linguistic resources
- n gram
- machine transliteration
- brazilian portuguese
- document clustering
- digital libraries
- machine learning