How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions.
Goran GlavasRobert LitschkoSebastian RuderIvan VulicPublished in: CoRR (2019)
Keyphrases
- cross lingual
- translation model
- parallel corpus
- word sense
- word segmentation
- language specific
- machine translation
- word alignment
- language modeling
- statistical machine translation
- indian languages
- language independent
- event extraction
- cross lingual information retrieval
- cross language
- machine translation system
- text classification
- n gram
- out of vocabulary
- word sense disambiguation
- sentiment classification
- co occurrence
- query translation
- source language
- bilingual dictionaries
- machine learning
- cross language information retrieval
- language model
- chinese english
- information extraction
- target language
- document clustering
- vector space
- dimensionality reduction