The future is different: Large pre-trained language models fail in prediction tasks.
Kostadin CvejoskiRamsés J. SánchezCésar OjedaPublished in: CoRR (2022)
Keyphrases
- language model
- pre trained
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- language modelling
- test collection
- retrieval model
- query expansion
- information retrieval
- training data
- smoothing methods
- statistical language models
- document ranking
- language models for information retrieval
- training examples
- bayesian networks
- clustering algorithm
- data sets
- spoken term detection