Privacy-Preserving Models for Legal Natural Language Processing
arXiv:2211.02956 · doi:10.18653/v1/2022.nllp-1.14
Abstract
Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to adversarial privacy attacks. In this paper, we asked to which extent we can guarantee privacy of pre-training data and, at the same time, achieve better downstream performance on legal tasks without the need of additional labeled data. We extensively experiment with scalable self-supervised learning of transformer models under the formal paradigm of differential privacy and show that under specific training configurations we can improve downstream performance without sacrifying privacy protection for the in-domain data. Our main contribution is utilizing differential privacy for large-scale pre-training of transformer language models in the legal NLP domain, which, to the best of our knowledge, has not been addressed before.
Camera ready, to appear at the Natural Legal Language Processing Workshop 2022 co-located with EMNLP
References in corpus (6)
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- BERT Goes to Law School: Quantifying the Competitive Advantage of Access to Large Legal Corpora in Contract Understanding
- How reparametrization trick broke differentially-private text representation learning
- The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization
- DP-Rewrite: Towards Reproducibility and Transparency in Differentially Private Text Rewriting
- One size does not fit all: Investigating strategies for differentially-private learning across NLP tasks