Fast Inference of Mixture-of-Experts Language Models with Offloading.
Artyom EliseevDenis MazurPublished in: CoRR (2023)
Keyphrases
- language model
- mixture model
- language modeling
- document retrieval
- speech recognition
- probabilistic model
- n gram
- information retrieval
- query expansion
- retrieval model
- smoothing methods
- statistical language models
- language modelling
- test collection
- context sensitive
- ad hoc information retrieval
- expert finding
- pseudo relevance feedback
- language models for information retrieval
- relevance model
- translation model
- document ranking
- vector space model
- okapi bm
- bayesian networks
- machine learning
- query terms
- question answering
- generative model
- word error rate
- expectation maximization
- language model for information retrieval