DP-NMT: Scalable Differentially Private Machine Translation
Timour Igamberdiev, Doan Nam Long Vu, Felix Kuennecke, Zhuo Yu, Jannik Holmer, Ivan Habernal
Abstract
Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility issues. To tackle this, we introduce DP-NMT, an open-source framework for carrying out research on privacy-preserving NMT with DP-SGD, bringing together numerous models, datasets, and evaluation metrics in one systematic software package. Our goal is to provide a platform for researchers to advance the development of privacy-preserving NMT systems, keeping the specific details of the DP-SGD algorithm transparent and intuitive to implement. We run a set of experiments on datasets from both general and privacy-related domains to demonstrate our framework in use. We make our framework publicly available and welcome feedback from the community.- Anthology ID:
- 2024.eacl-demo.11
- Volume:
- Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
- Month:
- March
- Year:
- 2024
- Address:
- St. Julians, Malta
- Editors:
- Nikolaos Aletras, Orphee De Clercq
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 94–105
- Language:
- URL:
- https://aclanthology.org/2024.eacl-demo.11
- DOI:
- Cite (ACL):
- Timour Igamberdiev, Doan Nam Long Vu, Felix Kuennecke, Zhuo Yu, Jannik Holmer, and Ivan Habernal. 2024. DP-NMT: Scalable Differentially Private Machine Translation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 94–105, St. Julians, Malta. Association for Computational Linguistics.
- Cite (Informal):
- DP-NMT: Scalable Differentially Private Machine Translation (Igamberdiev et al., EACL 2024)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2024.eacl-demo.11.pdf