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