Abstract
Text matching is an important task in natural language processing field, and it is widely used in intelligent question answering, information retrieval and other fields. With the rise of deep learning, text matching has gradually shifted from the traditional word similarity method to the neural network research. Currently, text matching methods based on deep learning are mainly divided into representation-based text matching models and interaction-based text matching models. Among them, the representation-based text matching model encodes two sentences separately, which easily loses the semantic focus and makes it difficult to measure the importance of context between sentences. The interaction-based text matching model ignores global information, and thus affects the global matching effect. Based on this, this paper proposes a multi-granularity text matching model combined with bidirectional attention (MGBA). The model enables two text tensors to interact in advance through the bidirectional attention mechanism, and then extracts the multi-granularity features of text tensors through LSTM and CNN, so that the model can focus on different levels of text information, thus solving the problem that traditional deep models tend to lose semantic focus and ignore global information in the process of text matching.
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
Xu, L., Li, S., Wang, Y., et al.: Named Entity Recognition of BERT-BiLSTM-CRF Combined with Self-attention. Springer, Cham (2021)
Li, H., Xu, J.: Semantic matching in search. Found. Trends Inf. Retr. 7(5), 343–469 (2014)
Xue, X., Jeon, J., Croft, W.B.: Retrieval models for question and answer archives. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2008, Singapore, 20–24 July. ACM (2008)
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)
Liang, P., Lan, Y., Guo, J., et al.: Text Matching as Image Recognition (2016)
Shen, Y., He, X., Gao, J., et al.: Learning semantic representations using convolutional neural networks for web search. In: Proceedings of the companion publication of the 23rd international conference on World wide web companion (2014)
Palangi, H., Deng, L., Shen, Y., et al.: Semantic modelling with long-short-term memory for information retrieval. Comput. Sci. (2015)
Yin, W., Schütze, H.: MultiGranCNN: an architecture for general matching of text chunks on multiple levels of granularity. In: Meeting of the Association for Computational Linguistics & the International Joint Conference on Natural Language Processing (2015)
Wan, S., Lan, Y., Guo. J., et al.: A deep architecture for semantic matching with multiple positional sentence representations. AAAI Press (2015)
Zhang, X, Lu, W., Zhang, G., et al.: Chinese sentence semantic matching based on multi-granularity fusion model (2020)
Devlin, J., Chang, M.W., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding (2018)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. 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)
Hu, B., Lu, Z., Hang, L., et al.: Convolutional neural network architectures for matching natural language sentences. Adv. Neural Inf. Process. Syst. 3 (2015)
Gong, Y., Luo, H., Zhang, J.: Natural language inference over interaction space (2017)
Seo, M., Kembhavi, A, Farhadi, A., et al.: Bidirectional attention flow for machine comprehension (2016)
Zhang, X.. et al.: Chinese sentence semantic matching based on multi-granularity fusion model. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, M., Zhang, J., Xu, L. (2022). Multi-granularity Chinese Text Matching Model Combined with Bidirectional Attention. In: Zhao, X., Yang, S., Wang, X., Li, J. (eds) Web Information Systems and Applications. WISA 2022. Lecture Notes in Computer Science, vol 13579. Springer, Cham. https://doi.org/10.1007/978-3-031-20309-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-20309-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20308-4
Online ISBN: 978-3-031-20309-1
eBook Packages: Computer ScienceComputer Science (R0)