Abstract
Multi-label Text Classification (MLTC) aims to learn a classifier that is able to automatically annotate a data point with the most relevant subset of labels from an large number of labels. Label semantics and relationships are important information for multi-label text classification. Existing methods tend to ignore explore high-order dependencies among labels. In this paper, a model called HRGCN (Hop-Residual graph convolutional network) is proposed to capture label dependency and label structure. The hop-connected graph convolutional network can obtain the deep dependence between the labels through a label graph, where the label graph constructed by a correlation matrix and a feature matrix represents the co-occurrence of the labels. Meanwhile, the self-attention mechanism allows to assign different weights to the text features extracted by BiGRU. Fusion of text representation and label representation to form label-text awareness to achieve interaction and generate multi-label classifiers for end-to-end training. Experimental results demonstrate that the proposed model achieves better performance compared to baseline models on the dataset RCV1-V2 and AAPD.
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
References
Katakis, I., Vlahavas, I., Tsoumakas, G.: Multilabel Text Classification for Automated Tag Suggestion (2008)
Gaonkar, R., Kwon, H., Bastan, M., et al.: Modeling label semantics for predicting emotional reactions. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)
Chang, W.C., Yu, H.F., Zhong, K., et al.: Taming Pretrained Transformers for Extreme Multi-label Text Classification (2019)
Gopal, S., Yang, Y.: Multilabel classification with meta-level features, pp. 315–322 (2010)
Bhatia, K., Jain, H., Kar, P., Varma, M., Jain, P.: Sparse local embeddings for extreme multi-label classification. In: Proceedings of NIPS, pp. 730–738 (2015)
Prabhu, Y., Varma, M.: FastXML: a fast, accurate and stable tree-classifier for extreme multi-label learning. ACM (2014)
You, R., Zhang, Z., Wang, Z., et al.: AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification (2018)
Jasinska, K., Dembczynski, K., Busa-Fekete, R., Pfannschmidt, K., Klerx, T., Hullermeier, E.: Extreme f-measure maximization using sparse probability estimates. In: ICML, pp. 1435–1444 (2016)
Liu, J., Chang, W.C., Wu, Y., et al.: Deep learning for extreme multi-label text classification. In: The 40th International ACM SIGIR Conference. ACM (2017)
Kim, Y.: Convolutional Neural Networks for Sentence Classification. Eprint Arxiv (2014)
Conneau, A., Schwenk, H., Barrault, L., et al.: Very deep convolutional networks for text classification. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: vol. 1, Long Papers (2017)
Yang, P., Xu, S., Wei, L., et al.: SGM: Sequence Generation Model for Multi-label Classification (2018)
Lin, J., Qi, S., Yang, P., et al.: Semantic-unit-based dilated convolution for multi-label text classification. In: Conference on Empirical Methods in Natural Language Processing (2018)
Cai, H., Zheng, V.W., Chang, C.C.: A comprehensive survey of graph embedding: problems, techniques and applications. IEEE Trans. Knowl. Data Eng. 30(9), 1616–1637 (2017)
Yao, L., Mao, C., Luo, Y.: Graph Convolutional Networks for Text Classification (2018)
Hong, H., Guo, H., Lin, Y., et al.: An Attention-based Graph Neural Network for Heterogeneous Structural Learning (2019)
Hao, P., Li, J., Yu, H., et al.: Large-scale hierarchical text classification with recursively regularized deep graph-CNN. In: The 2018 World Wide Web Conference (2018)
Pal, A., Selvakumar, M., Sankarasubbu, M.: MAGNET: multi-label text classification using attention-based graph neural network. In: 12th International Conference on Agents and Artificial Intelligence arXiv (2020)
Kipf, T.N., Welling, M.: Semi-Supervised Classification with Graph Convolutional Networks (2016)
Dey, R., Salemt, F.M.: Gate-variants of gated recurrent unit (GRU) neural networks. In: IEEE International Midwest Symposium on Circuits & Systems, pp. 1597–1600. IEEE (2017)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS, pp. 5998–6008 (2017)
Cho, K., Merrienboer, B.V., Gulcehre, C., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. Computer Science (2014)
Jain, H., Prabhu, Y., Varma, M.: Extreme Multi-label Loss Functions for Recommendation, Tagging, Ranking & Other Missing Label Applications, pp. 935–944. ACM (2016)
Xiao, L., Huang, X., Chen, B., Jing, L.: Label-specific document representation for multi-label text classification. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)
Acknowledgments
This work is supported by the Science & Technology project (41008114, 41011215, and 41014117).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Pu, T., Yin, S., Li, W., Xu, W. (2021). Graph Convolutional Network Exploring Label Relations for Multi-label Text Classification. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13032. Springer, Cham. https://doi.org/10.1007/978-3-030-89363-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-89363-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89362-0
Online ISBN: 978-3-030-89363-7
eBook Packages: Computer ScienceComputer Science (R0)