Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization.
Jilei WangShiying LuoWeiyan ShiTao DaiShu-Tao XiaPublished in: Rep4NLP@ACL (2018)
Keyphrases
- matrix factorization
- cross lingual
- word segmentation
- event extraction
- translation model
- indian languages
- mono lingual
- collaborative filtering
- parallel corpus
- language independent
- machine translation
- language modeling
- word sense
- recommender systems
- missing data
- statistical machine translation
- negative matrix factorization
- cross language
- text classification
- n gram
- bilingual dictionaries
- document clustering
- chinese english
- machine translation system
- monolingual retrieval
- parallel corpora
- machine learning
- dimensionality reduction
- transfer learning
- probabilistic model
- information extraction
- target language
- query translation
- vector space
- test collection
- information retrieval
- query expansion
- language model