Byte Pair Encoding is Suboptimal for Language Model Pretraining.
Kaj BostromGreg DurrettPublished in: CoRR (2020)
Keyphrases
- language model
- language modeling
- document retrieval
- retrieval model
- probabilistic model
- speech recognition
- query expansion
- n gram
- language modelling
- test collection
- ad hoc information retrieval
- information retrieval
- mixture model
- context sensitive
- pairwise
- pseudo relevance feedback
- relevance model
- statistical language models
- vector space model
- language models for information retrieval
- word clouds
- language model for information retrieval
- query terms
- expectation maximization