Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT.
Alexandra ChronopoulouDario StojanovskiAlexander M. FraserPublished in: CoRR (2020)
Keyphrases
- language model
- statistical machine translation
- language modeling
- comparable corpora
- n gram
- cross lingual
- document retrieval
- retrieval model
- probabilistic model
- translation model
- speech recognition
- language independent
- language modelling
- query expansion
- information retrieval
- parallel corpora
- machine translation
- statistical language models
- ad hoc information retrieval
- mixture model
- language model for information retrieval
- unsupervised learning
- context sensitive
- query terms
- vector space model
- chinese english
- smoothing methods
- test collection
- linguistic resources
- pseudo relevance feedback
- query translation
- error rate
- cross language information retrieval
- document length
- supervised learning
- semi supervised
- word clouds
- hidden markov models