Abstract
Question classification is the core of the question-and-answer (Q&A) sys-tem. This paper intends to use the method of deep learning to explore the question classification model in Q&A systems, the aim of which is to improve the accuracy of question classification.
The characteristics of natural language questions, such as the use of short texts and basic grammar, were well considered. Subsequently, we want to fully extract the features of questions by using the following methods: multi-channel inputs, multi-granularity convolution kernels, and direct connection with high-speed channels. By combining the three methods, this paper proposes the multi-channel and Bidirectional long-and short-term memory and multi- granularity convolution neural net-work (MC–BLSTM–MGCNN) model to fully extract the features from interrogative sentences, both in time and spatial domains.
To verify the validity of the model, this paper experimented with the TREC [1] classification standard dataset. Results achieved 96.6% accuracy, which is superior to the highest existing industry benchmark (96.1%). In addition, this paper used the complete TREC dataset to innovate further, and results obtained 98% accuracy, which greatly improved the classification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, X., Roth, D.: Learning question classifiers. In: Proceedings of the 19th International Conference on Computational Linguistics, vol. 1, pp. 1–7. Association for Computational Linguistics (2002)
Zhang, Y., Liu, T., et al.: Modified Bayesian model based question classification. J. Chin. Inf. Process. 19(2), 100–105 (2005). (in Chinese)
Wen, X., Zhang, Y., et al.: Syntactic structure parsing based chinese question classification. J. Chin. Inf. Process. 20(2), 33–39 (2006)
Sun, J.G., Cai, D.F., et al.: How Net based Chinese question automatic classification. J. Chin. Inf. Process. 21(1), 90–95 (2007). (in Chinese)
Silva, J., Coheur, L., et al.: From symbolic to sub-symbolic information in question classification. Artif. Intell. Rev. 35(2), 137–154 (2011)
Liu, L., Yu, Z., et al.: Chinese question classification based on question property kernel. J. Mach. Learn. Cybern. 5(5), 713–720 (2014)
Socher, R., Pennington, J., et al.: Semi-supervised recursive auto encoders for predicting sentiment distributions. In: Proceedings of the Empirical Methods in Natural Language Conference, pp. 151–161. Association for Computational Linguistics (2011)
Cui, L., Zhang, D., et al.: Learning topic representation for SMT with neural networks. In: Proceedings of the 52nd Annual Meeting, pp. 133–143. Association for Computational Linguistics (2014)
Blunsom, P., Grefenstette, E., et al.: A convolutional neural network for modelling sentences. In: Proceedings of the 52nd Annual Meeting, pp. 655–665. Association for Computational Linguistics (2014)
Dong, L., Wei, F., et al.: Question answering over freebase with multi-column convolutional neural networks. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pp. 260–269 (2015)
Zhang, D., Wang, D.: Relation classification via recurrent neural network. J. Comput. Sci. Process. (2015)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the Empirical Methods in Natural Language, pp. 1746–1751 (2014)
Irsoy, O., Cardie, C.: Deep recursive neural networks for compositionality in language. J. Adv. Neural Inf. Process. Syst. 2096–2104 (2014)
Lei, T., Barzilay, R., et al.: Molding CNNs for text: non-linear, non-consecutive convolutions. J. Indiana Univ. Math. Process. 58(3), 1151–1186 (2015)
Iyyer, M., Manjunatha, V., et al.: Deep unordered composition rivals syntactic methods for text classification. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (2015)
Tai, K.S., Socher, R., et al.: Improved semantic representations from tree-structured long short-term memory networks. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (2015)
Graves, A.: Generating sequences with recurrent neural networks. J. Comput. Sci. (2014)
Fang, I.-T.: Deep learning for query semantic domains classification (2016). http://cs224d.standford.edu/reports_2016.html
Kalchbrenner, N., Grefenstette, E., et al.: A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014)
Kim, Y.: Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882 (2014)
Mou, L., Peng, H., et al.: Discriminative neural sentence modeling by tree-based convolution. arXiv preprint arXiv:1504.01106 (2015)
Zhang, Y., Wallace, B.: A sensitivity analysis of convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820 (2015)
Zhou, P., Qi, Z.Y., et al.: Text classification improved by integrating bidirectional LSTM with two-dimensional max pooling. arXiv preprint arXiv:1611.06639 (2016)
Kiros, R., Zhu, Y.K., et al.: Skip-thought vectors. In: Advances in Neural Information Processing Systems, pp. 3295–3302 (2015)
Zhao, H., Lu, Z.D., et al.: Self-adaptive hierarchical sentence model. arXiv preprint arXiv:1504.05070 (2015)
Zhou, C., Sum, C., et al.: A C-LSTM neural network for text classification. J. Comput. Sci. 1(4), 39–44 (2015)
Zhang, R., Lee, H., et al.: Dependency sensitive convolutional neural networks for modeling sentences and documents. In: Proceedings of NAACL-HLT, pp. 1512–1521 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
E, H., Hu, Y., Song, M., Ou, Z., Wang, X. (2017). Research and Implementation of Question Classification Model in Q&A System. In: Ibrahim, S., Choo, KK., Yan, Z., Pedrycz, W. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2017. Lecture Notes in Computer Science(), vol 10393. Springer, Cham. https://doi.org/10.1007/978-3-319-65482-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-65482-9_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65481-2
Online ISBN: 978-3-319-65482-9
eBook Packages: Computer ScienceComputer Science (R0)