Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings.
Chenggang MiYating YangLei WangXi ZhouTonghai JiangPublished in: COLING (2018)
Keyphrases
- cross lingual
- translation model
- parallel corpus
- word segmentation
- machine translation
- word alignment
- word sense
- language specific
- statistical machine translation
- language modeling
- language independent
- cross lingual information retrieval
- indian languages
- machine translation system
- cross language
- out of vocabulary
- event extraction
- co occurrence
- bilingual dictionaries
- text classification
- language model
- word sense disambiguation
- vector space
- transfer learning
- n gram
- parallel corpora
- news articles
- information retrieval
- source language
- query translation
- document clustering
- low dimensional
- labeled data
- cross language information retrieval
- machine learning
- text mining
- information extraction