A BERT-based Heterogeneous Graph Convolution Approach for Mining Organization-Related Topics
Haoda Qian1,2; Minjie Yuan1,2; Qiudan Li1; Daniel Zeng1,2
2022-07
Conference Name2022 IEEE World Congress on Computational Intelligence
Pages0
Conference Date2022-07
Conference PlacePadua, Italy
Abstract

 

Mining organization-related topics is helpful to analyze and monitor the information dissemination situation. Existing methods based on heterogeneous graph neural networks mainly consider the association between words and documents, they ignore the semantic interactions between documents, and do not consider the heterogeneity of edges, which are difficult to solve the challenge of blurred topic boundaries in real scenarios, resulting in performance loss. This paper proposes a BERT-based Heterogeneous Graph Convolution Network (BERT-HGCN) approach for semi-supervised topic mining that comprehensively considers multi-semantic relations between words and documents. It deeply combines the advantages of transductive learning with labeled examples and pre-training models. We model documents as graph-structured data and capture the multiple semantic dependencies among word-word, word-doc, and doc-doc via neighborhood propagation. During the model learning process, a two-channel encoding mechanism is used to learn the structure and semantic representations, which fuses a hierarchical graph convolution network (HGCN) and a BERT-based DNN autoencoder. It simultaneously considers edges heterogeneity and semantics of original documents. Finally, a dual-supervised loss function is used to train a classifier based on graph nodes and semantic representations for topic mining. We empirically evaluate the performance of the proposed model on a real-world organization-related dataset, the experimental results demonstrate the efficacy of the model.

Other Abstract

 

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48609
Collection复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
Affiliation1.The State Key Laboratory of Management and Control for Complex Systems Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Haoda Qian,Minjie Yuan,Qiudan Li,et al. A BERT-based Heterogeneous Graph Convolution Approach for Mining Organization-Related Topics[C],2022:0.
Files in This Item: Download All
File Name/Size DocType Version Access License
A BERT-based Heterog(646KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Haoda Qian]'s Articles
[Minjie Yuan]'s Articles
[Qiudan Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Haoda Qian]'s Articles
[Minjie Yuan]'s Articles
[Qiudan Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Haoda Qian]'s Articles
[Minjie Yuan]'s Articles
[Qiudan Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A BERT-based Heterogeneous Graph Convolution Approach for Mining Organization-Related Topics_final (1).pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.