Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding.
Jie OuYueming ChenWenhong TianPublished in: CoRR (2024)
Keyphrases
- n gram
- language model
- language modeling
- viterbi algorithm
- language modelling
- probabilistic model
- document retrieval
- information retrieval
- variable length
- language independent
- bag of words
- finite state transducers
- query expansion
- retrieval model
- part of speech
- test collection
- speech recognition
- word segmentation
- text classification
- context sensitive
- statistical language modeling
- pseudo relevance feedback
- relevance model
- document ranking
- vector space model