A Graph Convolutional Network-Based Sensitive Information Detection Algorithm
In the field of natural language processing (NLP), the task of sensitive information detection refers to the procedure of identifying sensitive words for given documents. The majority of existing detection methods are based on the sensitive-word tree, which is usually constructed via the common pref...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2021/6631768 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832567889417207808 |
|---|---|
| author | Ying Liu Chao-Yu Yang Jie Yang |
| author_facet | Ying Liu Chao-Yu Yang Jie Yang |
| author_sort | Ying Liu |
| collection | DOAJ |
| description | In the field of natural language processing (NLP), the task of sensitive information detection refers to the procedure of identifying sensitive words for given documents. The majority of existing detection methods are based on the sensitive-word tree, which is usually constructed via the common prefixes of different sensitive words from the given corpus. Yet, these traditional methods suffer from a couple of drawbacks, such as poor generalization and low efficiency. For improvement purposes, this paper proposes a novel self-attention-based detection algorithm using the implementation of graph convolutional network (GCN). The main contribution is twofold. Firstly, we consider a weighted GCN to better encode word pairs from the given documents and corpus. Secondly, a simple, yet effective, attention mechanism is introduced to further integrate the interaction among candidate words and corpus. Experimental results from the benchmarking dataset of THUC news demonstrate a promising detection performance, compared to existing work. |
| format | Article |
| id | doaj-art-aca2cec2595f4257ad81f90e18dcb523 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-aca2cec2595f4257ad81f90e18dcb5232025-02-03T01:00:17ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/66317686631768A Graph Convolutional Network-Based Sensitive Information Detection AlgorithmYing Liu0Chao-Yu Yang1Jie Yang2School of Economics and Management, Anhui University of Science and Technology, Huainan, ChinaSchool of Economics and Management, Anhui University of Science and Technology, Huainan, ChinaFaculty of Engineering and Information Sciences, School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, AustraliaIn the field of natural language processing (NLP), the task of sensitive information detection refers to the procedure of identifying sensitive words for given documents. The majority of existing detection methods are based on the sensitive-word tree, which is usually constructed via the common prefixes of different sensitive words from the given corpus. Yet, these traditional methods suffer from a couple of drawbacks, such as poor generalization and low efficiency. For improvement purposes, this paper proposes a novel self-attention-based detection algorithm using the implementation of graph convolutional network (GCN). The main contribution is twofold. Firstly, we consider a weighted GCN to better encode word pairs from the given documents and corpus. Secondly, a simple, yet effective, attention mechanism is introduced to further integrate the interaction among candidate words and corpus. Experimental results from the benchmarking dataset of THUC news demonstrate a promising detection performance, compared to existing work.http://dx.doi.org/10.1155/2021/6631768 |
| spellingShingle | Ying Liu Chao-Yu Yang Jie Yang A Graph Convolutional Network-Based Sensitive Information Detection Algorithm Complexity |
| title | A Graph Convolutional Network-Based Sensitive Information Detection Algorithm |
| title_full | A Graph Convolutional Network-Based Sensitive Information Detection Algorithm |
| title_fullStr | A Graph Convolutional Network-Based Sensitive Information Detection Algorithm |
| title_full_unstemmed | A Graph Convolutional Network-Based Sensitive Information Detection Algorithm |
| title_short | A Graph Convolutional Network-Based Sensitive Information Detection Algorithm |
| title_sort | graph convolutional network based sensitive information detection algorithm |
| url | http://dx.doi.org/10.1155/2021/6631768 |
| work_keys_str_mv | AT yingliu agraphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm AT chaoyuyang agraphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm AT jieyang agraphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm AT yingliu graphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm AT chaoyuyang graphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm AT jieyang graphconvolutionalnetworkbasedsensitiveinformationdetectionalgorithm |