What Makes Pre-trained Language Models Better Zero-shot Learners?
Jinghui LuDongsheng ZhuWeidong HanRui ZhaoBrian Mac NameeFei TanPublished in: ACL (1) (2023)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- probabilistic model
- document retrieval
- language modelling
- information retrieval
- test collection
- speech recognition
- query expansion
- learning environment
- statistical language models
- retrieval model
- language models for information retrieval
- learning process
- control signals
- training data
- smoothing methods
- training examples
- relevance model
- e learning
- pairwise
- support vector
- data sets