标题： 面向语言模型的匿名化 显示英文标题

标题： Towards the Anonymization of the Language Modeling

摘要： 自然语言处理（NLP）的迅速发展已经革新了许多领域，包括医疗保健。 然而，这些进展引发了重要的隐私问题，特别是在微调并专门针对敏感数据的预训练模型可能会记住并暴露和重复个人信息的情况下。 本文提出了一种保护隐私的语言建模方法，以解决语言模型匿名化的问题，从而促进它们的共享。 具体来说，我们提出了一种掩码语言建模（MLM）方法，用于专门化类似BERT的语言模型，以及一种因果语言建模（CLM）方法，用于专门化类似GPT的模型，以避免模型记住训练数据中存在的直接和间接的身份信息。 我们使用医学数据集对我们的方法进行了全面评估，并与不同的基线进行了比较。 我们的结果表明，通过在模型专门化过程中避免记住直接和间接标识符，我们的掩码和因果语言建模方案在保持高隐私性的同时保留高实用性方面提供了良好的权衡。 显示英文摘要

摘要： 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.