Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora.
Takashi WadaTomoharu IwataYuji MatsumotoTimothy BaldwinJey Han LauPublished in: CoRR (2020)
Keyphrases
- cross lingual
- parallel corpora
- language independent
- cross lingual information retrieval
- machine translation
- bilingual dictionaries
- translation model
- word pairs
- parallel corpus
- machine translation system
- comparable corpora
- statistical machine translation
- cross language
- learning algorithm
- query translation
- out of vocabulary
- n gram
- cross language information retrieval
- language modeling
- news articles
- text classification
- reinforcement learning
- sentence level
- word alignment
- co occurrence
- query expansion
- active learning
- indian languages