Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt.
Gangwei JiangCaigao JiangSiqiao XueJames Y. ZhangJun ZhouDefu LianYing WeiPublished in: CoRR (2023)
Keyphrases
- fine tuning
- language model
- pre trained
- language modeling
- training data
- document retrieval
- speech recognition
- information retrieval
- probabilistic model
- training examples
- n gram
- test collection
- statistical language models
- retrieval model
- smoothing methods
- language modelling
- relevance model
- control signals
- query expansion
- document ranking
- fine tuned
- neural network
- multi modal
- high dimensional
- appearance variations