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 …

This study proposes a novel semi-supervised multi-label emotion classification approach for
French tweets based on pseudo-labeling. Human subjectivity in emotional expression …

In-Context Learning (ICL) combined with pre-trained large language models has achieved
promising results on various NLP tasks. However, ICL requires high-quality annotated …

The goal of this study is to solve the combined issue of noise labels and imbalanced
samples for text classification. Current studies generally adopt data sampling or cleaning in …

In this paper, we aim to generate text classification data given arbitrary class definitions (ie,
user instruction), so one can train a small text classifier without any human annotation or raw …

As the metaverse continues to expand, it becomes increasingly critical to have human-
centric networks that are both efficient and high-performing to optimize the user experience …

Recent works in relation extraction (RE) have achieved promising benchmark accuracy;
however, our adversarial attack experiments show that these works excessively rely on …

Recent advances in weakly supervised text classification mostly focus on designing
sophisticated methods to turn high-level human heuristics into quality pseudo-labels. In this …

When applying deep neural network language models to related systems (eg, question
answering systems, chatbots, and intelligent assistants), many datasets contain different …