Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries.
Mozhi ZhangYoshinari FujinumaMichael J. PaulJordan L. Boyd-GraberPublished in: CoRR (2020)
Keyphrases
- cross lingual
- bilingual dictionaries
- translation model
- parallel corpus
- word sense
- machine translation
- word segmentation
- language specific
- word alignment
- language modeling
- language independent
- parallel corpora
- statistical machine translation
- cross language
- cross lingual information retrieval
- query translation
- indian languages
- machine translation system
- text classification
- news articles
- out of vocabulary
- n gram
- vector space
- source language
- language model
- co occurrence
- decision trees
- cross language information retrieval
- low dimensional
- target language
- information retrieval systems
- word sense disambiguation
- machine learning
- multiword
- document clustering
- clustering algorithm
- chinese english