Cross-Lingual Word Embeddings for Turkic Languages.
Elmurod KuriyozovYerai DovalCarlos Gómez-RodríguezPublished in: LREC (2020)
Keyphrases
- cross lingual
- translation model
- language specific
- parallel corpus
- word segmentation
- word sense
- machine translation
- indian languages
- language independent
- statistical machine translation
- language modeling
- word alignment
- cross lingual information retrieval
- machine translation system
- cross language
- multi lingual
- out of vocabulary
- european languages
- n gram
- bilingual dictionaries
- text classification
- target language
- parallel corpora
- news articles
- co occurrence
- source language
- low dimensional
- query translation
- vector space
- document clustering
- character n grams
- word sense disambiguation
- language model
- machine learning
- dimensionality reduction
- wordnet
- linguistic resources
- information extraction
- natural language
- keywords
- transfer learning
- text documents