Towards Robust and Privacy-preserving Text Representations
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Written text often provides sufficient clues to identify the author, their gender, age, and other important attributes.Consequently, the authorship of training and evaluation corpora can have unforeseen impacts, including differing model performance for different user groups, as well as privacy implications.In this paper, we propose an approach to explicitly obscure important author characteristics at training time, such that representations learned are invariant to these attributes.Evaluating on two tasks, we show that this leads to increased privacy in the learned representations, as well as more robust models to varying evaluation conditions, including out-of-domain corpora.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“Model Our model is a bi-directional LSTM for POS tag prediction (Hochreiter and Schmidhuber, 1997), formulated as: for input sequence x i | ni =1 with terminal hidden states h 0 and h n +1 set to zero, where φ is a linear transformation, and [ · ; · ] denotes vector concatenation.”
MethodConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 1×
“This often comes at the cost of an accuracy reduction for models trained on the corrupted data (Shokri and Shmatikov, 2015; Abadi et al., 2016).”
BackgroundDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · cited 1×
“The transfered representations may still contain sensitive information, however, especially if an adversary has preliminary knowledge of the training model, in which case they can readily reverse engineer the input, for example, by a GAN attack algorithm (Hitaj et al., 2017).”
BackgroundMen Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 2×
“, gender correlating with class skews (Zhao et al., 2017), or translation choices (Rabinovich et al.”
BackgroundDemographic Factors Improve Classification Performance
Hovy, D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1073 · Cited by 148
Cited by
Mitigating Gender Bias in Natural Language Processing: Literature Review
Sun, T., Gaut, A., Tang, S., Huang, Y., ElSherief, M., Zhao, J., Mirza, D., Belding, E., Chang, K.-W., & Wang, W. Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1159 · Cited by 492
“Other important aspects such as model/data trans-parency (Mitchell et al., 2019; Bender and Fried-man, 2018) and privacy preservation (Reddy and Knight, 2016; Elazar and Goldberg, 2018; Li et al., 2018) are also not covered in this literature survey.”
BackgroundGenerative Adversarial Networks: A Survey Toward Private and Secure Applications
Cai, Z., Xiong, Z., Xu, H., Wang, P., Li, W., & Pan, Y. (2022) · ACM Computing Surveys · doi:10.1145/3459992 · Cited by 376
Predictive biases in natural language processing models: A conceptual framework and overview
Shah, D. S., Schwartz, H. A., & Hovy, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.468 · Cited by 241
“Li et al. (2018) introduced a model-based counter measure.”
BackgroundInfluentialAdversarial Removal of Demographic Attributes from Text Data
Elazar, Y., & Goldberg, Y. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1002 · Cited by 237
“Recent work on creating private representation in the text domain (Li et al., 2018) share our motivation of removing unintended demographic attributes from the learned representation using adversarial training.”
BackgroundInformation Leakage in Embedding Models
Song, C., & Raghunathan, A. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3417270 · Cited by 175
Metadata
- Authors
- Li, Y., Baldwin, T., & Cohn, T.
- Venue
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Published
- 2018
- Pages
- 25-30
- OpenAlex
- W2963879260
- Cited by
- 152
- References
- 8
- FWCI
- 9.05
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.