Training Compact Models for Low Resource Entity Tagging using Pre-trained Language Models.
Peter IzsakShira GuskinMoshe WasserblatPublished in: EMC2@NeurIPS (2019)
Keyphrases
- training samples
- language model
- probabilistic model
- training set
- training data
- pre trained
- language modeling
- feature space
- learning algorithm
- language modelling
- statistical language models
- relevance model
- smoothing methods
- n gram
- retrieval model
- document retrieval
- query expansion
- information retrieval
- face recognition
- speech recognition
- statistical model
- decision trees
- information retrieval systems
- feature extraction
- test collection