Weakly Supervised Text Classification

AbstractWeakly supervised text classification based on a few user-provided seed words has recently attracted much attention from researchers. Existing methods mainly generate pseudo-labels in a context-free manner (e.g., string matching), …...

AbstractWeakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided …...

AbstractWeakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these …...

AbstractIn weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assigned pseudo-labels and …...