Are Large Pre-Trained Language Models Leaking Your Personal Information?
Jie HuangHanyin ShaoKevin Chen-Chuan ChangPublished in: CoRR (2022)
Keyphrases
- personal information
- language model
- pre trained
- language modeling
- training data
- n gram
- training examples
- third party
- probabilistic model
- social networking
- speech recognition
- sensitive information
- language modelling
- information retrieval
- retrieval model
- query expansion
- smoothing methods
- control signals
- statistical language models
- relevance model
- decision trees
- neural network
- privacy preserving
- user interaction
- small number
- knowledge discovery
- active learning
- machine learning
- data sets