How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey.
Jun BaiXiaofeng ZhangChen LiHanhua HongXi XuChenghua LinWenge RongPublished in: EMNLP (Findings) (2023)
Keyphrases
- language model
- brute force
- fine tuning
- pre trained
- language modeling
- n gram
- fine tuned
- probabilistic model
- query expansion
- speech recognition
- information retrieval
- retrieval model
- context sensitive
- test collection
- ad hoc information retrieval
- exhaustive search
- training data
- computationally expensive
- mixture model
- data sets
- training examples
- statistical model
- generative model
- small number
- learning process
- smoothing methods
- control signals
- machine learning
- dirichlet prior
- neural network