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