Improving Cross-Lingual Word Embeddings by Meeting in the Middle.
Yerai DovalJosé Camacho-ColladosLuis Espinosa AnkeSteven SchockaertPublished in: EMNLP (2018)
Keyphrases
- cross lingual
- translation model
- parallel corpus
- language specific
- word segmentation
- machine translation
- word sense
- cross lingual information retrieval
- word alignment
- language independent
- statistical machine translation
- indian languages
- language modeling
- cross language
- machine translation system
- event extraction
- text classification
- out of vocabulary
- bilingual dictionaries
- n gram
- word sense disambiguation
- parallel corpora
- query translation
- co occurrence
- news articles
- mono lingual
- source language
- document clustering
- vector space
- low dimensional
- information retrieval systems
- dimensionality reduction
- machine learning algorithms
- text categorization
- language model
- feature selection
- data mining