Self-Selected Attention Span for Accelerating Large Language Model Inference.
Tian JinWanzin YazarZifei XuSayeh SharifyXin WangPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- query expansion
- speech recognition
- information retrieval
- retrieval model
- document retrieval
- test collection
- language modelling
- context sensitive
- bayesian networks
- smoothing methods
- statistical language models
- mixture model
- vector space model
- translation model
- bayesian inference
- ad hoc information retrieval
- relevance model
- document ranking
- retrieval effectiveness
- language models for information retrieval
- word clouds
- query specific
- dependency structure
- relevant documents
- pseudo feedback
- hidden markov models