期刊
2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021)
卷 -, 期 -, 页码 2803-2813出版社
ASSOC COMPUTATIONAL LINGUISTICS-ACL
关键词
-
类别
资金
- Alibaba Group through Alibaba Innovative Research Program
The paper proposes a novel framework called ClassKG to explore keyword-keyword correlation on keyword graph by GNN, which is an iterative process consisting of constructing keyword graph, training subgraph annotator, training text classifier, and re-extracting keywords from classified texts. Extensive experiments show that the proposed method outperforms existing ones on both long-text and short-text datasets.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据