Towards the Anonymization of the Language Modeling
This addresses privacy concerns in NLP for domains like healthcare, enabling safer sharing of models, though it appears incremental as it builds on existing BERT and GPT architectures.
The paper tackles the problem of language models memorizing and exposing personal information from sensitive data by proposing privacy-preserving masking and causal language modeling methodologies. The results show that these methods maintain high privacy while retaining high utility, as evaluated on a medical dataset.
Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on sensitive data can memorize and then expose and regurgitate personal information. This paper presents a privacy-preserving language modeling approach to address the problem of language models anonymization, and thus promote their sharing. Specifically, we propose both a Masking Language Modeling (MLM) methodology to specialize a BERT-like language model, and a Causal Language Modeling (CLM) methodology to specialize a GPT-like model that avoids the model from memorizing direct and indirect identifying information present in the training data. We have comprehensively evaluated our approaches using a medical dataset and compared them against different baselines. Our results indicate that by avoiding memorizing both direct and indirect identifiers during model specialization, our masking and causal language modeling schemes offer a good tradeoff for maintaining high privacy while retaining high utility.