SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.02591 · EMNLP · 2021

Weakly-supervised Text Classification Based on Keyword Graph

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

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 pseudolabels 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.02591")
get_code_for_paper("2110.02591")
have("2110.02591")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2110.02591.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2110.02591.svg)](https://syntology.ai/paper/2110.02591)

Connect an agent — have() is free.