Multiple weak supervision for short text classification

Abstract For short text classification, insufficient labeled data, data sparsity, and imbalanced classification have become three major challenges. this, we proposed multiple weak supervision, which can label unlabeled automatically. Different from prior work, the method generate probabilistic labels through conditional independent model. What’s more, experiments were conducted to verify effectiveness of supervision. According experimental results on public dadasets, real datasets synthetic datasets, problem be solved effectively by Notably, without reducing precision , recall F1-score improved adding distant supervision clustering, used meet different application needs.