HARE: HumAn pRiors, a key to small language model Efficiency.
Lingyun ZhangBin JinGaojian GeLunhui LiuXuewen ShenMingyong WuHouqian ZhangYongneng JiangShiqi ChenShi PuPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- n gram
- speech recognition
- query expansion
- dirichlet prior
- document retrieval
- retrieval model
- information retrieval
- language modelling
- mixture model
- context sensitive
- ad hoc information retrieval
- relevance model
- vector space model
- test collection
- language model for information retrieval
- pseudo relevance feedback
- document ranking
- smoothing methods
- statistical language models
- machine learning
- bayesian framework
- dependency structure
- query terms
- word error rate
- prior knowledge