Abstract
Graph neural networks (GNNs) can deal with complex network structures and model complex syntax structures in natural languages, which makes GNN outstanding in text classification tasks. However, most graph neural network approaches don’t seem to take full advantage of the topological gains from document graphs. In this paper, we propose a topologically enhanced text classification method to make full use of the structural features of corpus graph and sentence graph. Specifically, we construct two different graphs based on contextual information, called sentence graphs and corpus graphs, respectively. We extract the topological features of words from the corpus graph and inject them into the graph neural network model based on sentence graph classification. To better integrate the topological features, we propose an asynchronous weighted propagation scheme, which selectively fuses the topological features with the original features of the word nodes, and integrate document features to predict final results. A large number of experiments on eight datasets demonstrate the effectiveness of our method.
Similar content being viewed by others
References
Aggarwal CC, Zhai C (2012) A survey of text classification algorithms. Mining Text Data:163–222
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate international conference on learning representations
Cai H, Zheng WV, Chang CCK (2018) A comprehensive survey of graph embedding: Problems, techniques and applications. IEEE Trans Knowl Data Eng 30:1616–1637
Chiu PCJ, Nichols E (2016) Named entity recognition with bidirectional lstm-cnns. Transactions of the Association for Computational Linguistics:357–370
Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding north american chapter of the association for computational linguistics
Dyer C, Ballesteros M, Ling W, Matthews A, Smith AN (2015) Transition-based dependency parsing with stack long short-term memory. International workshop on the ACL2 theorem prover and its applications
Felbo B, Mislove A, Søgaard A, Rahwan I, Lehmann S (2017) Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. EMNLP, pp 1616–1626
Goyal P, Ferrara E (2018) Graph embedding techniques, applications, and performance: a survey. Knowl-Based Syst 151:78–94
Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. KDD, pp 855–864
Huang L, Ma D, Li S, Zhang X, Wang H (2019) Text level graph neural network for text classification. EMNLP/IJCNLP (1)3442–3448
Joulin A, Grave E, Bojanowski P, Mikolov T (2017) Bag of tricks for efficient text classification conference of the european chapter of the association for computational linguistics
Kim Y (2014) Convolutional neural networks for sentence classification. EMNLP, pp 1746–1751
Kingma PD, Ba LJ (2015) Adam: a method for stochastic optimization international conference on learning representations
Kipf NT, Welling M (2016) Variational graph auto-encoders coRR
Kipf NT, Welling M (2017) Semi-supervised classification with graph convolutional networks international conference on learning representations
Li W, Xu H (2014) Text-based emotion classification using emotion cause extraction. Expert Syst Appl 41(4):1742– 1749
Li Y, Tarlow D, Brockschmidt M, Zemel R (2015) Gated graph sequence neural networks international conference on learning representations
Linmei H, Yang T, Shi C, Ji H, Li X (2019) Heterogeneous graph attention networks for semi-supervised short text classification. EMNLP/IJCNLP (1)4820–4829
Liu X, Luo Z, Huang H (2018) Jointly multiple events extraction via attention-based graph information aggregation. EMNLP, pp 1247–1256
Liu X, You X, Zhang X, Wu J, Lv P (2020) Tensor graph convolutional networks for text classification national conference on artificial intelligence
Maaten VDL, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res
Marcheggiani D, Bastings J, Titov I (2018) Exploiting semantics in neural machine translation with graph convolutional networks. In: North american chapter of the association for computational linguistics, pp 486–492
Niepert M, Ahmed M, Kutzkov K (2012) Learning convolutional neural networks for graphs. ICML, pp 2014–2023
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
Pennington J, Socher R, Manning DC (2014) Glove: Global vectors for word representation. EMNLP, pp 1532–1543
Perozzi B, Al-Rfou’ R, Skiena S (2014) Deepwalk: online learning of social representations. KDD, pp 701–710
Phan XH, Nguyen LM, Horiguchi S (2008) Learning to classify short and sparse text and web with hidden topics from large-scale data collections. WWW, pp 91–100
Ribeiro FRL, Saverese HPP, Figueiredo RD (2017) struc2vec: Learning node representations from structural identity. In: KDD ’17: The 23rd ACM SIGKDD International conference on knowledge discovery and data mining halifax NS Canada August 2017, pp 385–394
Rios A, Kavuluru R (2015) Convolutional neural networks for biomedical text classification: application in indexing biomedical articles. In: Proceedings of the 6th ACM Conference on bioinformatics, computational biology and health informatics, pp 258–267
Roy A, Idan B, Yoram L (2019) Topological based classification using graph convolutional networks
Ryabinin M, Popov S, Prokhorenkova L, Voita E (2020) Embedding words in non vector space with unsupervised graph learning. EMNLP 2020, pp 7317–7331
S H, J S (1997) Long short-term memory. Neural Comput 9:1735–1780
Scarselli F, Gori M, Tsoi CA, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20:61–80
Shen D, Wang G, Wang W, Min RM, Su Q, Zhang Y, Li C, Henao R, Carin L (2018) Baseline needs more love: on simple word-embedding-based models and associated pooling mechanisms meeting of the association for computational linguistics
Siddhant G, Goutham R (2020) Bae: Bert based adversarial examples for text classification. EMNLP 2020, pp 6174–6181
Socher R, Perelygin A, Wu J, Chuang J, Manning CD, Ng A, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. Assoc Comput Linguist:1631–1642
Sun C, Qiu X, Xu Y, Huang X (2019) How to fine-tune bert for text classification?. CCL, pp 194–206
Tang J, Qu M, Mei Q (2015) Pte: Predictive text embedding through large-scale heterogeneous text networks. ACM Knowledge Discovery and Data Mining
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. WWW
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez NA, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems. 30 (NIPS 2017), pp 5998–6008
Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. ICLR
Wallach MH (2006) Topic modeling: beyond bag-of-words. ICML, pp 977–984
Wang S, Manning DC (2012) Baselines and bigrams: simple, good sentiment and topic classification. ACL
Wei L, Shuheng L, Shuming M, Yancheng H, Deli C, Xu S (2019) Recursive graphical neural networks for text classification
Wei P (2020) Short text classification via term graph
Yang Z, Yang D, Dyer C, He X, Smola JA, Hovy HE (2016) Hierarchical attention networks for document classification. HLT-NAACL, pp 1480–1489
Yao L, Mao C, Luo Y (2019) Graph convolutional networks for text classification national conference on artificial intelligence
Yufeng Z, Xueli Y, Zeyu C, Shu W, Zhongzhen W, Liang W (2020) Every document owns its structure: Inductive text classification via graph neural networks. ACL, pp 334– 339
Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. In: Annual Conference on Neural Information Processing Systems, pp 649–657
Zhang Y, Liu Q, Song L (2018) Sentence-state lstm for text representation meeting of the association for computational linguistics
Zhibin L, Pan D, Jian-Yun N (2020) Vgcn-bert: Augmenting bert with graph embedding for text classification. European Conference on Information Retrieval, pp 369–382
Zhou H, Ma Y, Li X (2021) Feature selection based on term frequency deviation rate for text classification. Appl Intell 6:3255–3274
Zhou P, Shi W, Tian J, Qi Z, Li B, Hao H, Xu B (2016) Attention-based bidirectional long short-term memory networks for relation classification. ACL
Acknowledgements
This research is supported by the National Natural Science Foundation of China (62077027), the Ministry of Science and Technology of the People’s Republic of China(2018YFC2002500), the Jilin Province Development and Reform Commission, China (2019C053-1), the Education Department of Jilin Province, China (JJKH20200993K), the Department of Science and Technology of Jilin Province, China (20200801002GH), and the European Union’s Horizon 2020 FET Proactive project “WeNet-The Internet of us” (No. 823783).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
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
Song, R., Giunchiglia, F., Zhao, K. et al. Graph topology enhancement for text classification. Appl Intell 52, 15091–15104 (2022). https://doi.org/10.1007/s10489-021-03113-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-03113-8