SMASH: Improving SMAll Language Models' Few-SHot Ability with Prompt-Based Distillation.
Yueqian WangChang LiuKai ChenXi WangDongyan ZhaoPublished in: EMNLP (Findings) (2022)
Keyphrases
- language model
- language modeling
- document retrieval
- probabilistic model
- n gram
- information retrieval
- speech recognition
- language modelling
- query expansion
- retrieval model
- ad hoc information retrieval
- test collection
- statistical language models
- query terms
- language models for information retrieval
- document ranking
- video sequences
- context sensitive
- pseudo relevance feedback
- relevance model
- video data
- language model for information retrieval
- word error rate
- key frames
- visual features
- translation model
- vector space model
- vector space