Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining.
Ivana KvapilíkováMikel ArtetxeGorka LabakaEneko AgirreOndrej BojarPublished in: CoRR (2021)
Keyphrases
- parallel corpus
- cross lingual
- language independent
- cross language information retrieval
- sentence pairs
- query translation
- machine translation system
- word alignment
- machine translation
- cross lingual information retrieval
- statistical machine translation
- text mining
- data mining
- knowledge discovery
- unsupervised manner
- semi supervised
- vector space
- parallel corpora
- low dimensional
- semantic space
- source language
- target language
- graphical models
- natural language