Efficient Streaming Language Models with Attention Sinks.
Guangxuan XiaoYuandong TianBeidi ChenSong HanMike LewisPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- document retrieval
- retrieval model
- n gram
- probabilistic model
- speech recognition
- test collection
- information retrieval
- context sensitive
- statistical language models
- language modelling
- query expansion
- vector space model
- relevance model
- data streams
- document collections
- passage retrieval
- smoothing methods
- query processing