Cramming: Training a Language Model on a single GPU in one day.
Jonas GeipingTom GoldsteinPublished in: ICML (2023)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- information retrieval
- speech recognition
- query expansion
- ad hoc information retrieval
- statistical language models
- retrieval model
- smoothing methods
- mixture model
- relevance model
- word clouds
- context sensitive
- translation model
- language model for information retrieval
- word error rate
- language modelling
- query specific
- dirichlet prior
- query terms
- probability distribution
- feature selection