Knowledge graph (KG) technology is a newly emerged knowledge representation method in
the field of artificial intelligence. Knowledge graphs can form logical map**s from cluttered …

Weakly-supervised text classification trains a classifier using the label name of each target
class as the only supervision, which largely reduces human annotation efforts. Most existing …

The ability of generative language models (GLMs) to generate text has improved
considerably in the last few years, enabling their use for generative data augmentation. In …

With the exponentially evolving trends in technology, IoT networks are vulnerable to serious
security issues, allowing intruders to break into networks without authorization and …

Weak supervision (WS) is a powerful method to build labeled datasets for training
supervised models in the face of little-to-no labeled data. It replaces hand-labeling data with …

Text classification is a well-studied and versatile building block for many NLP applications.
Yet, existing approaches require either large annotated corpora to train a model with or …

Few-shot continual relation extraction (CRE) aims to perpetually learn new relations through
a limited set of training samples. Its primary challenges include few-shot problems and …

In this paper, we present an innovative iterative approach to rule learning specifically
designed for (but not limited to) text-based data. Our method focuses on progressively …

Extracting structured data from visually rich documents like invoices, receipts, financial
statements, and tax forms is key to automating many business workflows. However, building …

随着信息技术的发展, 人工智能为疾病诊疗带来重要价值. 然而, 人工智能中存在算法偏见现象,
可导致医疗卫生资源分配不均等问题, 严重损害患者的健康公**. 算法偏见是人为偏见的技术化 …