Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens.
Weiyao LuoSuncong ZhengHeming XiaWeikang WangYan LeiTianyu LiuShuang ChenZhifang SuiPublished in: CoRR (2024)
Keyphrases
- language modeling
- language model
- information retrieval
- n gram
- query expansion
- retrieval model
- test collection
- document retrieval
- probabilistic model
- language modelling
- cross lingual
- mixture model
- speech recognition
- context sensitive
- term weighting
- expert finding
- translation model
- pseudo relevance feedback
- relevance model
- statistical language models
- document length
- query terms
- trec collections
- ad hoc information retrieval
- vector space model
- smoothing methods
- sentence retrieval
- document language models
- word error rate
- document ranking
- text mining
- digital libraries
- multimedia