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 …

Data augmentation, the artificial creation of training data for machine learning by
transformations, is a widely studied research field across machine learning disciplines …

Text data augmentation is an effective strategy for overcoming the challenge of limited
sample sizes in many natural language processing (NLP) tasks. This challenge is especially …

Disinformation and fake news have posed detrimental effects on individuals and society in
recent years, attracting broad attention to fake news detection. The majority of existing fake …

Large-scale language models such as GPT-3 are excellent few-shot learners, allowing them
to be controlled via natural text prompts. Recent studies report that prompt-based direct …

This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the
performance on text classification tasks. AEDA includes only random insertion of …

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 …

The visual classification performance of vision-language models such as CLIP has been
shown to benefit from additional semantic knowledge from large language models (LLMs) …

How to learn a better speech representation for end-to-end speech-to-text translation (ST)
with limited labeled data? Existing techniques often attempt to transfer powerful machine …

Abstract Sparsely activated Mixture-of-Experts (MoE) is becoming a promising paradigm for
multi-task learning (MTL). Instead of compressing multiple tasks' knowledge into a single …