Although the NLP community has adopted central differential privacy as a...
Protecting privacy in contemporary NLP models is gaining in importance. ...
Most tasks in NLP require labeled data. Data labeling is often done on
c...
Privatized text rewriting with local differential privacy (LDP) is a rec...
Pre-training large transformer models with in-domain data improves domai...
We present a new NLP task and dataset from the domain of the U.S. civil
...
Clinical NLP tasks such as mental health assessment from text, must take...
Text rewriting with differential privacy (DP) provides concrete theoreti...
Identifying, classifying, and analyzing arguments in legal discourse has...
As privacy gains traction in the NLP community, researchers have started...
Preserving privacy in training modern NLP models comes at a cost. We kno...
Differential privacy provides a formal approach to privacy of individual...
Graph convolutional networks (GCNs) are a powerful architecture for
repr...
Evaluating the trustworthiness of a model's prediction is essential for
...
Arguing without committing a fallacy is one of the main requirements of ...
Reasoning is a crucial part of natural language argumentation. In order ...
An important skill in critical thinking and argumentation is the ability...
Argument mining has become a popular research area in NLP. It typically
...
The goal of argumentation mining, an evolving research field in computat...