BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling.
Javier de la RosaEduardo G. PonferradaPaulo VillegasPablo González de Prado SalasManu RomeroMaría GranduryPublished in: CoRR (2022)
Keyphrases
- language model
- language modeling
- document retrieval
- n gram
- speech recognition
- retrieval model
- information retrieval
- probabilistic model
- language modelling
- query expansion
- mixture model
- test collection
- ad hoc information retrieval
- query terms
- context sensitive
- statistical language models
- vector space model
- translation model
- language model for information retrieval
- word error rate
- document ranking
- relevance model
- cross language retrieval
- dirichlet prior
- information retrieval systems
- training set