NAACL 2022findings19 citations

Weakly Supervised Text Classification using Supervision Signals from a Language Model

Ziqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, Yangqiu Song

Abstract

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, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.

BibTeX
@inproceedings{zeng-etal-2022-weakly,
    title = "Weakly Supervised Text Classification using Supervision Signals from a Language Model",
    author = "Zeng, Ziqian  and
      Ni, Weimin  and
      Fang, Tianqing  and
      Li, Xiang  and
      Zhao, Xinran  and
      Song, Yangqiu",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-naacl.176/",
    doi = "10.18653/v1/2022.findings-naacl.176",
    pages = "2295--2305"
}
Weakly Supervised Text Classification using Supervision Signals from a Language Model · NAACL 2022