Bi-Drop: Generalizable Fine-tuning for Pre-trained Language Models via Adaptive Subnetwork Optimization.
Shoujie TongHeming XiaDamai DaiTianyu LiuBinghuai LinYunbo CaoZhifang SuiPublished in: CoRR (2023)
Keyphrases
- fine tuning
- language model
- pre trained
- language modeling
- n gram
- information retrieval
- probabilistic model
- retrieval model
- document retrieval
- speech recognition
- language modelling
- test collection
- query expansion
- statistical language models
- fine tuned
- training data
- document ranking
- smoothing methods
- relevance model
- language models for information retrieval
- training examples
- control signals
- machine learning
- dimensionality reduction
- face recognition