Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces.
Ivan VulicAnna KorhonenGoran GlavasPublished in: RepL4NLP@ACL (2020)
Keyphrases
- post processing
- bilingual lexicon
- vector space
- cross language
- machine translation
- cross language information retrieval
- comparable corpora
- preprocessing
- question answering
- text retrieval
- cross lingual
- similarity search
- query translation
- retrieval model
- translation model
- parallel corpora
- distance measure
- language independent
- document collections
- machine learning
- machine translation system
- document retrieval
- text categorization
- query expansion
- statistical machine translation
- bilingual dictionaries
- information access
- information retrieval
- word alignment
- semi supervised
- low dimensional
- domain specific
- language model
- information extraction
- parallel corpus
- supervised learning
- co occurrence
- feature extraction
- news articles
- data mining