Compressing Context to Enhance Inference Efficiency of Large Language Models.
Yucheng LiBo DongChenghua LinFrank GuerinPublished in: CoRR (2023)
Keyphrases
- language model
- context sensitive
- language modeling
- probabilistic model
- n gram
- statistical language models
- speech recognition
- query expansion
- document retrieval
- information retrieval
- mixture model
- retrieval model
- language modelling
- okapi bm
- pseudo relevance feedback
- language model for information retrieval
- vector space model
- test collection
- co occurrence
- context dependent
- document ranking
- query terms
- word error rate
- ad hoc information retrieval
- information extraction