Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning.
Xiaomeng HuShi YuChenyan XiongZhenghao LiuZhiyuan LiuGe YuPublished in: CoRR (2022)
Keyphrases
- fine tuning
- supervised learning
- learning algorithm
- learning to rank
- reinforcement learning
- learning process
- structured prediction
- knowledge acquisition
- fine tuned
- recurrent networks
- computer assisted instruction
- training process
- learning tasks
- online learning
- decision trees
- learning machines
- domain specific
- active learning
- learning environment