Abstract
Differential Privacy (DP) has been tailored to address the unique challenges of text-to-text privatization. However, text-to-text privatization is known for degrading the performance of language models when trained on perturbed text. Employing a series of interpretation techniques on the internal representations extracted from BERT trained on perturbed pre-text, we intend to disentangle at the linguistic level the distortion induced by differential privacy. Experimental results from a representational similarity analysis indicate that the overall similarity of internal representations is substantially reduced. Using probing tasks to unpack this dissimilarity, we find evidence that text-to-text privatization affects the linguistic competence across several formalisms, encoding localized properties of words while falling short at encoding the contextual relationships between spans of words.- Anthology ID:
- 2023.blackboxnlp-1.5
- Volume:
- Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, Hosein Mohebbi
- Venues:
- BlackboxNLP | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 65–75
- Language:
- URL:
- https://aclanthology.org/2023.blackboxnlp-1.5
- DOI:
- 10.18653/v1/2023.blackboxnlp-1.5
- Cite (ACL):
- Stefan Arnold, Nils Kemmerzell, and Annika Schreiner. 2023. Disentangling the Linguistic Competence of Privacy-Preserving BERT. In Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 65–75, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Disentangling the Linguistic Competence of Privacy-Preserving BERT (Arnold et al., BlackboxNLP-WS 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.blackboxnlp-1.5.pdf