This is the authors' abstract. We don't add key points for this paper.
Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and "this article is talking about [MASK]." A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AG-News, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zeng et al. (2022) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: