Abstract
Text categorization is a foundational task in many NLP applications. Traditional text classifiers often rely on hand engineering features, and recently Convolutional Neural Networks (CNNs) with word vectors have achieved remarkably better performance than traditional methods [15, 20]. In this paper, we combined prior knowledge into deep learning method for structured text categorization. In our model, we apply word embedding to capture both semantic and syntactic information of words, and apply different convolutional neural networks to capture advanced features of different parts of the structured text. Since different text parts perform different impact on the text categorization result, a linear SVM kernel is then applied to decide the final categorization result. Moreover, in order to enhance discriminativeness of the word, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings based on both words and their topics. We conduct experiments on several datasets. The experimental results show that our model outperforms typical text categorization models, especially when the text in the dataset have a similar structure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Schwenk, H., Senécal, J.S., et al.: A neural probabilistic language model. J. Mach. Learn. Res. 3(6), 1137–1155 (2003)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. JMLR 3, 993–1022 (2003)
Cai, L., Hofmann, T.: Text categorization by boosting automatically extracted concepts. In: SIGIR, pp. 182–189 (2003)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by backpropagating errors. In: Anderson, J.A., Rosenfeld, E. (eds.) Neurocomputing: Foundations of Research, pp. 696–699. MIT Press, Cambridge (1988)
Dumais, S., Platt, J., Heckerman, D., Sahami, M.: Inductive learning algorithms and representations for text categorization. In: Proceedings of the Seventh International Conference on Information and Knowledge Management, pp. 148–155. ACM Press (1998)
Elman, J.L.: Finding struture in time. Cogn. Sci. 14(90), 179–211 (1990)
Fragos, K., Maistros, I., Skourlas, C.: A X2-weighted maximum entropy model for text classification. In: Proceedings of 2nd International Conference on Natural Language Understanding and Cognitive Science, Miami, Florida, pp. 22–23 (2005)
Goyal, R.D.: Knowledge based neural network for text classification. In: IEEE International Conference on Granular Computing, p. 542 (2007)
Griffiths, T.L., Steyvers, M.: Finding scientific topics. PNAS 101, 5228–5235 (2004)
Grossman, D., Domingos, P.: Learning Bayesian network classifiers by maximizing conditional likelihood. In: Proceedings of the Twenty-First International Conference on Machine Learning, pp. 361–368. ACM Press (2005)
Hamad, A.: Weighted naive Bayesian classifier. In: IEEE/ACS International Conference, on Computer Systems and Applications, AICCSA apos 2007, vol. 1(1), pp. 437–441 (2007)
Hingmire, S., Chougule, S., Palshikar, G.K., Chakraborti, S.: Document classification by topic labeling. In: SIGIR, pp. 877–880 (2013)
Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398. Springer, Heidelberg (1998)
Kalchbrenner, N., Grefenstette, E., Blunsom, P.: A convolutional neural network for modelling sentences. Eprint Arxiv, p. 1 (2014)
Kim, Y.: Convolutional neural networks for sentence classification. Eprint Arxiv (2014)
Le, Q.V., Mikolov, T.: Distributed representations of sentences and documents. Eprint Arxiv, vol. 4, pp. 1188–1196 (2014)
Liu, P., Qiu, X., Huang, X.: Learning context-sensitive word embeddings with neural tensor skip-gram model. In: International Conference on Artificial Intelligence. AAAI Press (2015)
Liu, Y., Liu, Z., Chua, T.S., et al.: Topical word embeddings. In: Twenty-Ninth AAAI Conference on Artificial Intelligence. AAAI Press (2015)
Mikolov, T., Yih, W.-T., Zweig, G.: Linguistic regularities in continuous space word representations. In: NAACL-HLT, pp. 746–751 (2013)
Johnson, R., Zhang, T.: Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058 (2014)
Lai, S., Xu, L., Liu, K., Zhao, J.: Recurrent convolutional neural networks for text classification. In: Proceeding of the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2267–2273 (2014)
Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., Manning, C.D.: Semi-supervised recursive autoen-coders for predicting sentiment distributions. In: EMNLP, pp. 151–161 (2011)
Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: EMNLP, pp. 1631–1642 (2013)
Wang, S., Manning, C.D.: Baselines and bigrams: simple, good sentiment and topic classification. In: Meeting of the Association for Computational Linguistics: Short Papers, pp. 90–94 (2012)
Boureau, Y.-L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: International Conference on Machine Learning, p. 459 (2010)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Zeng, L., Li, Z.: Text classification based on paragraph distributed representation and extreme learning machine. In: Tan, Y., Shi, Y., Buarque, F., Gelbukh, A., Das, S., Engelbrecht, A. (eds.) ICSI-CCI 2015. LNCS, vol. 9141, pp. 81–88. Springer, Heidelberg (2015)
Zhang, X., Zhao, J., Lecun, Y.: Character-level convolutional networks for text classification. In: Neural Information Processing Systems (2015)
Acknowledgments
The authors would like to thank the anonymous reviewers for the constructive comments. This work was sponsored by the National Natural Science Foundation of China (No. 61303214 and No. 61303025, project approval number: U1536204).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Liu, J., Xu, Y., Deng, J., Wang, L., Zhang, L. (2016). Ld-CNNs: A Deep Learning System for Structured Text Categorization Based on LDA in Content Security. In: Chen, J., Piuri, V., Su, C., Yung, M. (eds) Network and System Security. NSS 2016. Lecture Notes in Computer Science(), vol 9955. Springer, Cham. https://doi.org/10.1007/978-3-319-46298-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-46298-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-46297-4
Online ISBN: 978-3-319-46298-1
eBook Packages: Computer ScienceComputer Science (R0)