How Much Knowledge Can You Pack Into the Parameters of a Language Model?
Adam RobertsColin RaffelNoam ShazeerPublished in: EMNLP (1) (2020)
Keyphrases
- language model
- language modeling
- n gram
- mixture model
- document retrieval
- retrieval model
- language modelling
- probabilistic model
- context sensitive
- language models for information retrieval
- statistical language models
- query expansion
- maximum likelihood
- speech recognition
- dirichlet prior
- ad hoc information retrieval
- prior knowledge
- document ranking
- test collection
- information retrieval
- word error rate
- vector space model
- language model for information retrieval