基于双超图神经网络特征融合的文本分类

doi:10.19678/j.issn.1000-3428.0068324

摘要/Abstract

摘要：

近年来, 图神经网络(GNN)在文本分类任务中受到广泛应用。当前基于GNN的文本分类模型首先将文本建模为图, 然后使用GNN对文本图进行特征传播与聚合, 但是此类方法有两点不足: 一是现有模型由于图结构的限制无法捕获单词之间的高阶语义关系; 二是现有模型无法捕获文本中的关键语义信息。为了解决上述问题, 提出一种基于双超图卷积网络特征融合的文本分类模型。一方面, 使用原始文本建立文本超图; 另一方面, 为短文本引入外部知识, 使用基于SenticNet词库的外部知识对文本进行语义增强, 构建语义超图。经过超图卷积后通过注意力机制对双超图特征进行融合, 实现短文本分类。在4个文本分类数据集上的实验结果表明, 该模型优于基线模型, 具有优越的文本分类性能。

关键词: 文本分类, 超图, 特征融合, SenticNet词库, 自然语言处理

Abstract:

In recent years, Graph Neural Networks (GNNs) have been widely used for text classification tasks. Current models based on GNNs first model the text as a graph and then use GNNs to propagate and aggregate the features of the text graph. However, these methods have two notable limitations. First, existing models cannot capture high-order semantic relationships between words because of the limitations of graph structures. Second, existing models cannot capture key semantic information from the text. To address these issues, this paper proposes a text classification model based on the feature fusion of dual hypergraph convolutional networks. On one hand, the original text is used to construct a text hypergraph; on the other hand, external knowledge is introduced for short texts. The text is semantically enhanced using external knowledge based on the SenticNet lexicon, and a semantic hypergraph is constructed. After hypergraph convolution, an attention mechanism is used to fuse the features of the dual hypergraphs for short-text classification. Experimental results on four text classification datasets show that the proposed model outperforms the baseline methods and demonstrates superior text classification performance.

Key words: text classification, hypergraph, feature fusion, SenticNet lexicon, natural language processing

郑诚, 李鹏飞. 基于双超图神经网络特征融合的文本分类[J]. 计算机工程, 2025, 51(6): 127-135.

ZHENG Cheng, LI Pengfei. Text Classification Based on Feature Fusion of Dual Hypergraph Neural Networks[J]. Computer Engineering, 2025, 51(6): 127-135.

https://www.ecice06.com/CN/Y2025/V51/I6/127

图/表 13

图1 常规文本图

Fig.1 Conventional text graph

图2 模型结构

Fig.2 Model structure

图3 超图结构示意图

Fig.3 Schematic diagram of hypergraph structure

图4 双超图构建

Fig.4 Dual hypergraph construction

图5 超图卷积

Fig.5 Hypergraph convolution

图6 特征融合

Fig.6 Feature fusion

图7 嵌入维度对R8分类效果的影响

Fig.7 Classification effect of embedding dimension on the R8

图8 嵌入维度对R52分类效果的影响

Fig.8 Classification effect of embedding dimension on the R52

图9 训练集比率对R8分类效果的影响

Fig.9 Classification effect of training set ratio on the R8

图10 训练集比率对R52分类效果的影响

Fig.10 Classification effect of training set ratio on the R52

参考文献 35

1	NOBLE W S . What is a support vector machine?. Nature Biotechnology, 2006, 24, 1565- 1567. doi: 10.1038/nbt1206-1565
2	ALFEILAT H A A , HASSANAT A B A , LASASSMEH O , et al. Effects of distance measure choice on k-nearest neighbor classifier performance: a review. Big Data, 2019, 7 (4): 221- 248. doi: 10.1089/big.2018.0175
3	HARRIS Z S . Distributional structure. Word, 1954, 10 (2/3): 146- 162.
4	SALTON G , WONG A , YANG C S . A vector space model for automatic indexing. Communications of the ACM, 1975, 18 (11): 613- 620. doi: 10.1145/361219.361220
5	MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2023-08-04]. https://arxiv.org/abs/1301.3781v3.
6	ALBAWI S, MOHAMMED T A, AL-ZAWI S. Understanding of a convolutional neural network[C]//Proceedings of the International Conference on Engineering and Technology (ICET). Washington D.C., USA: IEEE Press, 2017: 1-6.
7	MEDSKER L , JAIN L C . Recurrent neural networks: design and applications. Boca Raton, USA: CRC Press, 1999.
8	YAO L, MAO C S, LUO Y, et al. Graph convolutional networks for text classification[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence and 31st Innovative Applications of Artificial Intelligence Conference and 9th AAAI Symposium on Educational Advances in Artificial Intelligence. New York, USA: ACM Press, 2019: 7370-7377.
9	HUANG L Z, MA D H, LI S J, et al. Text level graph neural network for text classification[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Stroudsburg, USA: ACL Press, 2019: 3444-3450.
10	DING K Z, WANG J L, LI J D, et al. Be more with less: hypergraph attention networks for inductive text classification[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, USA: ACL Press, 2020: 4927-4936.
11	陈杰. 基于多方面特征表示与图卷积网络的短文本分类研究[D]. 合肥: 安徽大学, 2022.
	CHEN J. Research on short text classification based on multifaceted feature representation and graph convolution network[D]. Hefei: Anhui University, 2022. (in Chinese)
12	CAMBRIA E, SPEER R, HAVASI C, et al. SenticNet: a publicly available semantic resource for opinion mining[EB/OL]. [2023-08-04]. https://www.semanticscholar.org/paper/SenticNet%3A-A-Publicly-Available-Semantic-Resource-Cambria-Speer/8ae2d6c78c067acaa17713614c0d7d6b0a53baa8.
13	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法. 计算机科学, 2022, 49 (8): 230- 236.
	YAN J D , JIA C Y . Text classification method based on information fusion of dual-graph neural network. Computer Science, 2022, 49 (8): 230- 236.
14	KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, USA: ACL Press, 2014: 1746-1751.
15	ZHANG X, ZHAO J B, LECUN Y, et al. Character-level convolutional networks for text classification[C]//Proceedings of the 29th International Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2015: 649-657.
16	LIU P F, QIU X P, HUANG X J. Recurrent neural network for text classification with multi-task learning[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 2873-2879.
17	JANG B , KIM M , HARERIMANA G , et al. Bi-LSTM model to increase accuracy in text classification: combining Word2Vec CNN and attention mechanism. Applied Sciences, 2020, 10 (17): 5841. doi: 10.3390/app10175841
18	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2023-08-04]. https://arxiv.org/abs/1609.02907v4.
19	LIU X E, YOU X X, ZHANG X, et al. Tensor graph convolutional networks for text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2020: 8409-8416.
20	ZHANG Y F, YU X L, CUI Z Y, et al. Every document owns its structure: inductive text classification via graph neural networks[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL Press, 2020: 334-339.
21	RUIZ L , GAMA F , RIBEIRO A , et al. Gated graph sequence neural networks. IEEE Transactions on Signal Processing, 2020, 68, 6303- 6318. doi: 10.1109/TSP.2020.3033962
22	FENG Y F, YOU H X, ZHANG Z Z, et al. Hypergraph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2019: 3558-3565.
23	JELODAR H , WANG Y L , YUAN C , et al. Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications, 2019, 78 (11): 15169- 15211. doi: 10.1007/s11042-018-6894-4
24	杨世刚, 刘勇国. 融合语料库特征与图注意力网络的短文本分类方法. 计算机应用, 2022, 42 (5): 1324- 1329.
	YANG S G , LIU Y G . Short text classification method by fusing corpus features and graph attention network. Journal of Computer Applications, 2022, 42 (5): 1324- 1329.
25	YANG T C , HU L M , SHI C , et al. HGAT: heterogeneous graph attention networks for semi-supervised short text classification. ACM Transactions on Information Systems, 2021, 39 (3): 1- 29.
26	DAI Y , SHOU L J , GONG M , et al. Graph fusion network for text classification. Knowledge-Based Systems, 2022, 236, 107659. doi: 10.1016/j.knosys.2021.107659
27	ZHANG C, ZHU H, PENG X, et al. Hierarchical information matters: text classification via tree based graph neural network[C]//Proceedings of the 29th International Conference on Computational Linguistics. Stroudsburg, USA: ACL Press, 2022: 950-959.
28	HUANG Y H, CHEN Y H, CHEN Y S. ConTextING: granting document-wise contextual embeddings to graph neural networks for inductive text classification C]//Proceedings of the 29th International Conference on Computational Linguistics. Stroudsburg, USA: ACL Press, 2022: 1163-1168.
29	KENTON J D M W C, TOUTANOVA L K. BERT: pre-training of deep bidirectional Transformers for language understanding[C]//Proceedings of NAACL-HLT'19. Stroudsburg, USA: ACL Press, 2019: 4171-4186.
30	VASWANI A, SHAZEER N, PARMERN, et al. Attention is all you need[C]//Proceedings of the 31th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 6000-6010.
31	PENNINGTON J, SOCHER R, MANNING C. GloVe: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, USA: ACL Press, 2014: 1532-1543.
32	ZHANG M X , LI X M , YUE S B , et al. An empirical study of TextRank for keyword extraction. IEEE Access, 2020, 8, 178849- 178858. doi: 10.1109/ACCESS.2020.3027567
33	WANG K Z, HAN S C, POON J. InducT-GCN: inductive graph convolutional networks for text classification[C]//Proceedings of the 26th International Conference on Pattern Recognition (ICPR). Washington D.C., USA: IEEE Press, 2022: 1243-1249.
34	LIN C H, HE Y L, LIN C H, et al. Joint sentiment/topic model for sentiment analysis[C]//Proceedings of the 18th ACM Conference on Information and Knowledge Management. New York, USA: ACM Press, 2009: 375-384.
35	ZHU H, KONIUSZ P. Simple spectral graph convolution[C]//Proceedings of the International Conference on Learning Representation. New York, USA: ACM Press, 2021: 151-163.

[1]	刘凯, 任洪逸, 李蓥, 季怡, 刘纯平. 基于交叉模态注意力特征增强的医学视觉问答[J]. 计算机工程, 2025, 51(6): 49-56.
[2]	李毅, 徐慧英, 朱信忠, 黄晓, 王舒梦, 李悉钰. 基于YOLOv5n模型改进的口罩检测算法:Mask-YOLO[J]. 计算机工程, 2025, 51(6): 297-310.
[3]	曹蓓, 赵奎. 基于双重情感和多特征融合的虚假新闻检测[J]. 计算机工程, 2025, 51(6): 193-203.
[4]	李白芽. 基于CNN-Transformer的电子喉镜病灶及器官分割网络[J]. 计算机工程, 2025, 51(6): 327-337.
[5]	郝志峰, 黎阳霖, 许柏炎, 蔡瑞初. 面向跨域自然语言生成SQL语句的超图神经网络[J]. 计算机工程, 2025, 51(5): 114-123.
[6]	黄尧, 柴志雷. 基于通信和拓扑感知的SNN分区与映射算法[J]. 计算机工程, 2025, 51(5): 219-228.
[7]	庄紫薇, 朱俊国. 面向多源文本的越南语文本检错方法[J]. 计算机工程, 2025, 51(5): 93-102.
[8]	徐永刚, 孙琦烜, 李凡甲, 程健维, 戴佳俊. 基于扩展时间和时空特征融合图卷积网络的骨架行为识别[J]. 计算机工程, 2025, 51(4): 281-292.
[9]	杜晨阳, 张雪英, 黄丽霞, 李娟. 基于改进高效通道注意力机制的多特征语音情感识别[J]. 计算机工程, 2025, 51(4): 97-106.
[10]	栾方军, 龚琪, 袁帅. 基于注意力机制和多尺度融合的人群计数网络[J]. 计算机工程, 2025, 51(3): 352-361.
[11]	杨旺达, 万亚平, 邹刚, 闵晓珊, 王沂, 陆宇程. 驾驶素质缺失测试眼状态的深度学习分类方法研究[J]. 计算机工程, 2025, 51(2): 149-158.
[12]	李伟康, 张思全. 掩模特征融合: 实例分割新范式[J]. 计算机工程, 2025, 51(2): 126-138.
[13]	许明, 屈泰澎, 姜彦吉. 改进YOLOv7在复杂场景下的交通标志检测算法[J]. 计算机工程, 2025, 51(2): 335-343.
[14]	李猛坤, 袁晨, 王琪, 赵冲, 陈景轩, 刘立峰. 基于改进YOLOv8算法的在线听课行为识别模型研究[J]. 计算机工程, 2025, 51(1): 287-294.
[15]	费涛, 艾山·吾买尔, 杜文旭, 朱翠翠. 基于Squeezeformer的多颗粒度多方面发音质量评测方法[J]. 计算机工程, 2025, 51(1): 81-87.

选择文件类型/文献管理软件名称

选择包含的内容