A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models.
Yuanxin LiuFandong MengZheng LinJiangnan LiPeng FuYanan CaoWeiping WangJie ZhouPublished in: NeurIPS (2022)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- win win
- probabilistic model
- statistical language models
- query expansion
- speech recognition
- retrieval model
- smoothing methods
- information retrieval
- partial occlusion
- relevance model
- language models for information retrieval
- third party
- principal component analysis
- training data
- machine learning