Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where
deep learning techniques may fail. It is widely applied in computer vision then introduced to …

Large language models (LLMs) can be used to generate text data for training and evaluating
other models. However, creating high-quality datasets with LLMs can be challenging. In this …

Multi-label text classification (MLTC) involves tagging a document with its most relevant
subset of labels from a label set. In real applications, labels usually follow a long-tailed …

Motivation Few-shot learning that can effectively perform named entity recognition in low-
resource scenarios has raised growing attention, but it has not been widely studied yet in the …

Large models, encompassing large language and diffusion models, have shown
exceptional promise in approximating human-level intelligence, garnering significant …

The generation of synthetic data can be used for anonymization, regularization,
oversampling, semi-supervised learning, self-supervised learning, and several other tasks …

We introduce GENIUS: a conditional text generation model using sketches as input, which
can fill in the missing contexts for a given sketch (key information consisting of textual spans …

We present DALE, a novel and effective generative Data Augmentation framework for low-
resource LEgal NLP. DALE addresses the challenges existing frameworks pose in …

The few-shot natural language understanding (NLU) task has attracted much recent
attention. However, prior methods have been evaluated under a disparate set of protocols …