WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.
Benjamin MinixhoferFabian PaischerNavid RekabsazPublished in: CoRR (2021)
Keyphrases
- cross lingual
- language modeling
- language model
- n gram
- translation model
- speech recognition
- retrieval model
- cross lingual information retrieval
- pseudo feedback
- language independent
- language modeling framework
- out of vocabulary
- cross language
- cross language retrieval
- probabilistic model
- query expansion
- information retrieval
- document retrieval
- machine translation
- text classification
- parallel corpus
- statistical machine translation
- vector space model
- query translation
- parallel corpora
- transfer learning
- context sensitive
- vector space
- test collection
- pseudo relevance feedback
- relevance model
- query terms
- smoothing methods
- word segmentation
- machine translation system
- word alignment
- news articles
- search engine