[HTML][HTML] How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing
Deep learning (DL) models for natural language processing (NLP) tasks often handle
private data, demanding protection against breaches and disclosures. Data protection laws …
private data, demanding protection against breaches and disclosures. Data protection laws …
Null it out: Guarding protected attributes by iterative nullspace projection
The ability to control for the kinds of information encoded in neural representation has a
variety of use cases, especially in light of the challenge of interpreting these models. We …
variety of use cases, especially in light of the challenge of interpreting these models. We …
The text anonymization benchmark (tab): A dedicated corpus and evaluation framework for text anonymization
We present a novel benchmark and associated evaluation metrics for assessing the
performance of text anonymization methods. Text anonymization, defined as the task of …
performance of text anonymization methods. Text anonymization, defined as the task of …
Investigating gender bias in language models using causal mediation analysis
Many interpretation methods for neural models in natural language processing investigate
how information is encoded inside hidden representations. However, these methods can …
how information is encoded inside hidden representations. However, these methods can …
Measuring and reducing gendered correlations in pre-trained models
Pre-trained models have revolutionized natural language understanding. However,
researchers have found they can encode artifacts undesired in many applications, such as …
researchers have found they can encode artifacts undesired in many applications, such as …
A novel estimator of mutual information for learning to disentangle textual representations
Learning disentangled representations of textual data is essential for many natural language
tasks such as fair classification, style transfer and sentence generation, among others. The …
tasks such as fair classification, style transfer and sentence generation, among others. The …
Societal biases in retrieved contents: Measurement framework and adversarial mitigation of bert rankers
Societal biases resonate in the retrieved contents of information retrieval (IR) systems,
resulting in reinforcing existing stereotypes. Approaching this issue requires established …
resulting in reinforcing existing stereotypes. Approaching this issue requires established …
Learning disentangled textual representations via statistical measures of similarity
P Colombo, G Staerman, N Noiry… - arXiv preprint arXiv …, 2022 - arxiv.org
When working with textual data, a natural application of disentangled representations is fair
classification where the goal is to make predictions without being biased (or influenced) by …
classification where the goal is to make predictions without being biased (or influenced) by …
Causal mediation analysis for interpreting neural nlp: The case of gender bias
Common methods for interpreting neural models in natural language processing typically
examine either their structure or their behavior, but not both. We propose a methodology …
examine either their structure or their behavior, but not both. We propose a methodology …
A survey on out-of-distribution evaluation of neural nlp models
Adversarial robustness, domain generalization and dataset biases are three active lines of
research contributing to out-of-distribution (OOD) evaluation on neural NLP models …
research contributing to out-of-distribution (OOD) evaluation on neural NLP models …