Prompt-based Pseudo-labeling Strategy for Sample-Efficient Semi-Supervised Extractive Summarization

arXiv:2311.09559v2 Announce Type: replace
Abstract: Semi-supervised learning (SSL) is a widely used technique in scenarios where labeled data is scarce and unlabeled data is abundant. While SSL is popular for image and text classification, it is relatively underexplored for the task of extractive text summarization. Standard SSL methods follow a teacher-student paradigm to first train a classification model and then use the classifier's confidence values to select pseudo-labels for the subsequent training cycle; however, such classifiers are not suitable to …

abstract arxiv classification cs.ai cs.cl data image labeling paradigm popular prompt sample semi-supervised semi-supervised learning ssl standard strategy summarization supervised learning text text classification text summarization type