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"
}