Pseudo Labeling

AbstractWe consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given. Although heuristic methods based on pseudo-labeling …...

AbstractIn this paper, we introduce a state-of-the-art pseudo-labeling technique for few-shot intent detection. We devise a folding/unfolding hierarchical clustering algorithm which assigns weighted pseudo-labels to unlabeled user utterances. We show …...

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 …...

AbstractLabeling large amounts of extractive summarization data is often prohibitive expensive due to time, financial, and expertise constraints, which poses great challenges to incorporating summarization system in practical applications. This …...

AbstractSemi-supervised text classification (SSTC) aims at text classification with few labeled data and massive unlabeled data. Recent works achieve this task by pseudo-labeling methods, with the belief that the unlabeled …...