Gradient-based Intra-attention Pruning on Pre-trained Language Models.
Ziqing YangYiming CuiXin YaoShijin WangPublished in: CoRR (2022)
Keyphrases
- language model
- pre trained
- language modeling
- document retrieval
- n gram
- probabilistic model
- speech recognition
- information retrieval
- language modelling
- retrieval model
- training data
- training examples
- query expansion
- language models for information retrieval
- test collection
- statistical language models
- smoothing methods
- control signals
- relevance model
- text mining
- hidden markov models
- learning algorithm