Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification
Seongmin Park, Kyungho Kim, Jihwa Lee · 2023
Text classification with extremely weak supervision (EWS) imposes stricter supervision constraints compared to regular weakly supervised classification.Absolutely no labeled training samples or hand-crafted rules specific to the evaluation data are allowed.Such restrictions limit state-of-the-art EWS classification methods to indirect weak labeling techniques that assign unnatural label uncertainty estimates.We present PLAT, a framework that creates weak labels by leveraging recent developments in zero-shot text classification.PLAT employs models trained for sub-tasks other than classification to label documents.Most importantly, PLAT refrains from assigning overly confident weak labels and improves soft-label training performance for downstream classifiers.Classifiers trained with PLAT significantly outperform those trained on weak labels generated by the previous state-of-the-art in extremely weakly supervised text classification.