Abstract
Graph convolutional network (GCN) has a strong ability to extract the global feature but neglects the order of the words, thus leading to its weak effect on short text classification. In contrast, convolutional neural network (CNN) can capture the local contextual information within a sentence. There are few methods that can effectively classify both long text and short text. Therefore, we propose an ensemble convolutional network by combining GCN and CNN. In our method, GCN catches the global information and CNN extracts local features. Besides, we propose a simplified boosting algorithm, which makes CNN learn the samples misclassified by GCN again to improve classification performance and reduce the training time of the network. The results on four benchmark datasets show that our framework achieves better performance than other state-of-the-art methods with less memory.
Similar content being viewed by others
References
Battaglia PW, Hamrick JB, Bapst V, Sanchez-Gonzalez A, Zambaldi V, Malinowski M, Tacchetti A, Raposo D, Santoro A, Faulkner R, et al (2018) Relational inductive biases, deep learning, and graph networks. arXiv:1806.01261
Cheng W, Greaves C, Warren M (2006) From n-gram to skipgram to concgram. Int J Corpus Linguist 11(4):411–433
Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:181004805
Elakkiya E, Selvakumar S, Velusamy RL (2020) Textspamdetector: textual content based deep learning framework for social spam detection using conjoint attention mechanism. J Ambient Intell Human Comput 12:1–16
Gao H, Chen Y, Ji S (2019) Learning graph pooling and hybrid convolutional operations for text representations. In: The world wide web conference, pp 2743–2749
Haonan L, Huang SH, Ye T, Xiuyan G (2019) Graph star net for generalized multi-task learning. arXiv:190612330
Huang L, Ma D, Li S, Zhang X, Wang H (2019) Text level graph neural network for text classification. arXiv:191002356
James F (2005) The elements of statistical learning: data mining, inference and prediction. Math Intell 27(2):83–85
Kim Y (2014) Convolutional neural networks for sentence classification. corr abs/1408.5882. arXiv:14085882
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:14126980
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:160902907
Kuznetsov V, Mochalov V, Mochalova A (2015) Ontological-semantic text analysis and the question answering system using data from ontology. In: 2016 18th International conference on advanced communication technology (ICACT). IEEE, pp 651–658
Li F, Zhang M, Fu G, Qian T, Ji D (2016) A bi-lstm-rnn model for relation classification using low-cost sequence features. arXiv:160807720
Li Q, Peng H, Li J, Xia C, Yang R, Sun L, Yu PS, He L (2020) A survey on text classification: from shallow to deep learning. arXiv:200800364
Liang J, Deng Y, Zeng D (2020) A deep neural network combined cnn and gcn for remote sensing scene classification. IEEE J Sel Top Appl Earth Observ Remote Sens 13:4325–4338
Lin Y, Meng Y, Sun X, Han Q, Kuang K, Li J, Wu F (2021) Bertgcn: transductive text classification by combining gcn and bert. arXiv:210505727
Liu G, Li B, Hu W, Yang J (2013) Horror text recognition based on generalized expectation criteria. In: international conference on intelligent science and big data engineering. Springer, pp 136–142
Liu P, Qiu X, Huang X (2016) Recurrent neural network for text classification with multi-task learning. arXiv:160505101
Lu Z, Du P, Nie JY (2020) Vgcn-bert: augmenting bert with graph embedding for text classification. In: European conference on information retrieval. Springer, pp 369–382
Novotnỳ V, Ayetiran EF, Štefánik M, Sojka P (2020) Text classification with word embedding regularization and soft similarity measure. arXiv:200305019
Peng H, Li J, He Y, Liu Y, Bao M, Wang L, Song Y, Yang Q (2018) Large-scale hierarchical text classification with recursively regularized deep graph-cnn. In: Proceedings of the 2018 world wide web conference, pp 1063–1072
Peng H, Li J, Wang S, Wang L, Gong Q, Yang R, Li B, Yu P, He L (2019) Hierarchical taxonomy-aware and attentional graph capsule rcnns for large-scale multi-label text classification. IEEE Trans Knowl Data Eng 33(6):2505–2519
Shao K, Zhang Z, He S, Bo X (2020) Dtigccn: prediction of drug-target interactions based on gcn and cnn. In: 2020 IEEE 32nd international conference on tools with artificial intelligence (ICTAI). IEEE, pp 337–342
Socher R, Perelygin A, Wu J, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1631–1642
Tong X, Wu B, Wang S, Lv J (2018) A complaint text classification model based on character-level convolutional network. In: 2018 IEEE 9th international conference on software engineering and service science (ICSESS). IEEE, pp 507–511
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv:170603762
Wang SI, Manning CD (2012) Baselines and bigrams: Simple, good sentiment and topic classification. In: Proceedings of the 50th annual meeting of the association for computational linguistics (volume 2: short papers), pp 90–94
Wu F, Souza A, Zhang T, Fifty C, Yu T, Weinberger K (2019) Simplifying graph convolutional networks. In: International conference on machine learning, PMLR, pp 6861–6871
Xu B, Guo X, Ye Y, Cheng J (2012) An improved random forest classifier for text categorization. JCP 7(12):2913–2920
Xu D, Ruan C, Korpeoglu E, Kumar S, Achan K (2020) Inductive representation learning on temporal graphs. arXiv:200207962
Yadav RK, Jiao L, Granmo OC, Goodwin M (2021) Enhancing interpretable clauses semantically using pretrained word representation. In: Proceedings of the fourth BlackboxNLP workshop on analyzing and interpreting neural networks for NLP, pp 265–274
Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification. Proc AAAI Conf Artif Intell 33:7370–7377
Zaheer M, Guruganesh G, Dubey A, Ainslie J, Alberti C, Ontanon S, Pham P, Ravula A, Wang Q, Yang L, et al. (2020) Big bird: transformers for longer sequences. arXiv:200714062
Zhang YD, Satapathy SC, Guttery DS, Górriz JM, Wang SH (2021) Improved breast cancer classification through combining graph convolutional network and convolutional neural network. Inf Process Manag 58(2):102439
Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M (2020) Graph neural networks: a review of methods and applications. AI Open 1:57–81
Zhu H, Koniusz P (2021) Simple spectral graph convolution. In: International conference on learning representations
Zukov-Gregoric A, Bachrach Y, Minkovsky P, Coope S, Maksak B (2017) Neural named entity recognition using a self-attention mechanism. In: 2017 IEEE 29th international conference on tools with artificial intelligence (ICTAI). IEEE, pp 652–656
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zeng, F., Chen, N., Yang, D. et al. Simplified-Boosting Ensemble Convolutional Network for Text Classification. Neural Process Lett 54, 4971–4986 (2022). https://doi.org/10.1007/s11063-022-10843-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-022-10843-4