Weakly-supervised Text Classification Based on Keyword Graph

Lu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu, Shuigeng Zhou


Abstract
Weakly-supervised text classification has received much attention in recent years for it can alleviate the heavy burden of annotating massive data. Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts. However, existing methods treat keywords independently, thus ignore the correlation among them, which should be useful if properly exploited. In this paper, we propose a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN. Our framework is an iterative process. In each iteration, we first construct a keyword graph, so the task of assigning pseudo labels is transformed to annotating keyword subgraphs. To improve the annotation quality, we introduce a self-supervised task to pretrain a subgraph annotator, and then finetune it. With the pseudo labels generated by the subgraph annotator, we then train a text classifier to classify the unlabeled texts. Finally, we re-extract keywords from the classified texts. Extensive experiments on both long-text and short-text datasets show that our method substantially outperforms the existing ones.
Anthology ID:
2021.emnlp-main.222
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2803–2813
Language:
URL:
https://aclanthology.org/2021.emnlp-main.222
DOI:
10.18653/v1/2021.emnlp-main.222
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.222.pdf
Code
 zhanglu-cst/classkg
Data
AG NewsIMDb Movie Reviews