Abstract
Deep learning has been widely used in text matching tasks. However, the existing deep learning models are mainly designed for short texts matching and cannot be directly applied to the search of scientific papers. The main reason is that the differences between long and short texts in scientific paper search have not been fully considered, and the structural information of the text will be lost when the length difference is large. In order to solve the above long-short scientific text matching problem, we propose a multi-view relevance matching model (MVRM) of scientific papers based on graph convolutional network and attention mechanism. First, we use scientific papers abstract to construct interactive graph to retain the structural information in the long text. Each vertex denotes the keyword in the abstract and the edge weight denotes similarity between the keywords. Second, we propose a matching network for interactive graph based on the graph convolution networks. Multiple keywords in the search term form multiple views, and each keyword under each view interacts with the interactive graph. Then the interaction feature vectors from multiple views are generated through graph convolution network. Finally, attention mechanism is used for fusion, and the final matching result is output through the multilayer perceptron. Experiments on several representative scientific paper search datasets demonstrate that our model achieves better performance.
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
Robertson, S., Zaragoza, H.: The Probabilistic Relevance Framework: BM25 and Beyond. Now Publishers Inc. (2009)
Huang, P.S., He, X., Gao, J., et al.: Learning deep structured semantic models for web search using clickthrough data. In: Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, pp. 2333–2338 (2013)
Wan, S., Lan, Y., Guo, J., et al.: A deep architecture for semantic matching with multiple positional sentence representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1 (2016)
Hu, B., Lu, Z., Li, H., et al.: Convolutional neural network architectures for matching natural language sentences. arXiv preprint arXiv:1503.03244 (2015)
Pang, L., Lan, Y., Guo, J., et al.: Text matching as image recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30, no. 1 (2016)
Subramanian, S., Trischler, A., Bengio, Y., et al.: Learning general purpose distributed sentence representations via large scale multi-task learning. arXiv preprint arXiv:1804.00079 (2018)
Logeswaran, L., Lee, H.: An efficient framework for learning sentence representations. arXiv preprint arXiv:1803.02893 (2018)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)
Gong, Y., Luo, H., Zhang, J.: Natural language inference over interaction space. arXiv preprint arXiv:1709.04348 (2017)
Tay, Y., Tuan, L.A., Hui, S.C.: Multi-cast attention networks. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2299–2308 (2018)
Wang, Z., Fan, Y., Guo, J., et al.: Match\(^2\): a matching over matching model for similar question identification. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 559–568 (2020)
Rao, J., Liu, L., Tay, Y., et al.: Bridging the gap between relevance matching and semantic matching for short text similarity modeling. 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), pp. 5373–5384 (2019)
Yang, R., Zhang, J., Gao, X., et al.: Simple and effective text matching with richer alignment features. arXiv preprint arXiv:1908.00300 (2019)
Liu, B., Niu, D., Wei, H., et al.: Matching article pairs with graphical decomposition and convolutions. arXiv preprint arXiv:1802.07459 (2018)
Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pp. 404–411 (2004)
Shen, Y., He, X., Gao, J., et al.: Learning semantic representations using convolutional neural networks for web search. In: Proceedings of the 23rd International Conference on World Wide Web, pp. 373–374 (2014)
Guo, J., Fan, Y., Ai, Q., et al.: A deep relevance matching model for ad-hoc retrieval. In: Proceedings of the 25th ACM International Conference on Information and Knowledge Management, pp. 55–64 (2016)
Chen, Q., Zhu, X., Ling, Z., et al.: Enhanced LSTM for natural language inference. arXiv preprint arXiv:1609.06038 (2016)
Acknowledgements
This work was supported by National Key R&D Program of China (2018YFB1402600), and by the National Natural Science Foundation of China (61802028, 61772083, 61877006, 62002027), and sponsored by CCF-Baidu Open Fund.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Song, J., Xue, Z., Du, J., Kou, F., Liang, M., Xu, M. (2021). Multi-view Relevance Matching Model of Scientific Papers Based on Graph Convolutional Network and Attention Mechanism. In: Fang, L., Chen, Y., Zhai, G., Wang, J., Wang, R., Dong, W. (eds) Artificial Intelligence. CICAI 2021. Lecture Notes in Computer Science(), vol 13069. Springer, Cham. https://doi.org/10.1007/978-3-030-93046-2_61
Download citation
DOI: https://doi.org/10.1007/978-3-030-93046-2_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93045-5
Online ISBN: 978-3-030-93046-2
eBook Packages: Computer ScienceComputer Science (R0)