SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models.
Vithursan ThangarasaAbhay GuptaWilliam MarshallTianda LiKevin LeongDennis DeCosteSean LieShreyas SaxenaPublished in: UAI (2023)
Keyphrases
- language model
- fine tuning
- language modeling
- fine tuned
- probabilistic model
- n gram
- retrieval model
- speech recognition
- document retrieval
- viable alternative
- statistical language models
- information retrieval
- test collection
- language modelling
- query expansion
- ad hoc information retrieval
- document ranking
- smoothing methods
- context sensitive
- translation model
- training set
- word error rate
- relevance model
- term dependencies
- machine learning
- okapi bm
- vector space model
- language models for information retrieval