DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling.
Shikhar TuliChi-Heng LinYen-Chang HsuNiraj K. JhaYilin ShenHongxia JinPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- context sensitive
- probabilistic model
- query expansion
- information retrieval
- language modelling
- document retrieval
- speech recognition
- test collection
- retrieval model
- language model for information retrieval
- statistical language models
- bayesian inference
- pseudo relevance feedback
- document ranking
- query specific
- ad hoc information retrieval
- bayesian networks
- markov chain monte carlo
- translation model
- document length
- mixture model
- retrieval effectiveness
- error rate
- word error rate
- language models for information retrieval