Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting
and enhance their generalization and performance, various methods have been suggested …

Data augmentation has recently seen increased interest in NLP due to more work in low-
resource domains, new tasks, and the popularity of large-scale neural networks that require …

Data augmentation (DA) is indispensable in modern machine learning and deep neural
networks. The basic idea of DA is to construct new training data to improve the model's …

In this work, we provide a survey of active learning (AL) for its applications in natural
language processing (NLP). In addition to a fine-grained categorization of query strategies …

NLP has achieved great progress in the past decade through the use of neural models and
large labeled datasets. The dependence on abundant data prevents NLP models from being …

Improving the generalization of deep networks is an important open challenge, particularly
in domains without plentiful data. The mixup algorithm improves generalization by linearly …

Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity
on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set …

Despite recent successes, most contrastive self-supervised learning methods are domain-
specific, relying heavily on data augmentation techniques that require knowledge about a …

Large Language Models have demonstrated remarkable few-shot performance, but the
performance can be sensitive to the selection of few-shot instances. We propose PATRON, a …

We study the problem of learning neural text classifiers without using any labeled data, but
only easy-to-provide rules as multiple weak supervision sources. This problem is …