Training Compute-Optimal Large Language Models.
Jordan HoffmannSebastian BorgeaudArthur MenschElena BuchatskayaTrevor CaiEliza RutherfordDiego de Las CasasLisa Anne HendricksJohannes WelblAidan ClarkTom HenniganEric NolandKatie MillicanGeorge van den DriesscheBogdan DamocAurelia GuySimon OsinderoKaren SimonyanErich ElsenJack W. RaeOriol VinyalsLaurent SifrePublished in: CoRR (2022)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- information retrieval
- document retrieval
- language modelling
- query expansion
- statistical language models
- speech recognition
- test collection
- retrieval model
- context sensitive
- query terms
- smoothing methods
- retrieval effectiveness
- language model for information retrieval
- word error rate
- vector space model
- document ranking
- term dependencies
- translation model
- tf idf
- document length
- image retrieval
- training set