Abstract
Chinese sentence semantic matching is a fundamental task in natural language processing, which aims to distinguish whether two Chinese sentences are semantically similar or not. Originated from English semantic matching task, most existing matching methods merely focus on learning the sentence representation from word granularity, but neglect the uniqueness of Chinese characters and the semantic interactions within a sentence on different granularities, and the interactions between sentences. As a result, most existing matching methods on Chinese language only achieve very limited performance improvement. In the paper, we propose a multi-perspective interactive (MPI) model for Chinese sentence semantic matching, which first employs a multi-granularity encoding layer to transform the characters and words in sentences into their embedding representation, then devises a multi-perspective interactive layer to capture the intra-sentence interactions within a sentence but on different granularities and the inter-sentence interactions between sentences. Finally, a prediction layer takes all the captured interactions as input to estimate the matching degree. We also conduct extensive experiments on real-world data set to assess the model performance. The extensive experimental results demonstrate that our proposed model achieves significantly better performance than the compared benchmarks.
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
Notes
- 1.
Codes are available at https://github.com/baoshuo/MPI.
References
Cer, D., et al.: Universal sentence encoder for English. In: Proceedings of EMNLP, pp. 169–174 (2018)
Chen, L., et al.: Neural graph matching networks for Chinese short text matching. In: Proceedings of ACL, pp. 6152–6158 (2020)
Chen, Q., Zhu, X., Ling, Z.H., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. In: Proceedings of ACL, pp. 1657–1668 (2017)
Gu, J.C., et al.: Speaker-aware BERT for multi-turn response selection in retrieval-based chatbots. In: Proceedings of CIKM, pp. 2041–2044 (2020)
He, T., Huang, W., Qiao, Y., Yao, J.: Text-attentional convolutional neural network for scene text detection. In: Proceedings of the IEEE Transactions on Image Processing, vol. 25, no. 6, 2529–2541 (2016)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Huang, J., Yao, S., Lyu, C., Ji, D.: Multi-granularity neural sentence model for measuring short text similarity. In: Candan, S., Chen, L., Pedersen, T.B., Chang, L., Hua, W. (eds.) DASFAA 2017. LNCS, vol. 10177, pp. 439–455. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-55753-3_28
Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
Kim, S., Kang, I., Kwak, N.: Semantic sentence matching with densely-connected recurrent and co-attentive information. In: Proceedings of AAAI, vol. 33, pp. 6586–6593 (2019)
Lai, Y., Feng, Y., Yu, X., Wang, Z., Xu, K., Zhao, D.: Lattice CNNs for matching based Chinese question answering. In: Proceedings of AAAI, vol. 33, pp. 2786–6641 (2019)
Laskar, M.T.R., Huang, X., Hoque, E.: Contextualized embeddings based transformer encoder for sentence similarity modeling in answer selection task. In: Proceedings of The 12th Language Resources and Evaluation Conference, pp. 5505–5514 (2020)
Liu, W., Zhou, P., Wang, Z., Zhao, Z., Deng, H., Ju, Q.: FastBERT: a self-distilling BERT with adaptive inference time. In: Proceedings of ACL, pp. 6035–6044 (2020)
Liu, X., et al.: LCQMC: A large-scale Chinese question matching corpus. In: Proceedings of the COLING, pp. 1952–1962 (2018)
Lu, W., Yu, R., Wang, S., Wang, C., Jian, P., Huang, H.: Sentence semantic matching based on 3D CNN for human-robot language interaction. In: Proceedings of ACM Transactions on Internet Technology (TOIT), vol. 21, no. 4, pp. 1–24 (2021)
Lyu, B., Chen, L., Zhu, S., Yu, K.: Let: Linguistic knowledge enhanced graph transformer for Chinese short text matching. In: Proceedings of the AAAI, vol. 35, pp. 13498–13506 (2021)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: Proceedings of the AAAI, vol. 30, pp. 2786–2792 (2016)
Su, J.: Text emotion classification (iv): Better loss function. https://spaces.ac.cn/archives/4293
Sun, Y., et al.: Ernie: Enhanced representation through knowledge integration. arXiv preprint arXiv:1904.09223 (2019)
Wang, S., et al.: Cross-thought for sentence encoder pre-training. In: Proceedings of the EMNLP, pp. 412–421 (2020)
Wang, Z., Hamza, W., Florian, R.: Bilateral multi-perspective matching for natural language sentences. In: Proceedings of the IJCAI, pp. 4144–4150 (2017)
Yang, R., Zhang, J., Gao, X., Ji, F., Chen, H.: Simple and effective text matching with richer alignment features. In: Proceedings of ACL, pp. 4699–4709 (2019)
Zhang, S., Tan, H., Chen, L., Lv, B.: Enhanced text matching based on semantic transformation. IEEE Access 8, 30897–30904 (2020)
Acknowledgment
The research work is partly supported by National Key R&D Program of China under Grant No.2018YFC0830705 and No.2018YFC0831700, National Natural Science Foundation of China under Grant No.61502259, and Key Program of Science and Technology of Shandong Province under Grant No.2020CXGC010901 and No.2019JZZY020124. Wenpeng Lu is the corresponding author.
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
Kan, B., Lu, W., Li, F., Wu, H., Zhao, P., Zhang, X. (2021). Multi-Perspective Interactive Model for Chinese Sentence Semantic Matching. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13111. Springer, Cham. https://doi.org/10.1007/978-3-030-92273-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-030-92273-3_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92272-6
Online ISBN: 978-3-030-92273-3
eBook Packages: Computer ScienceComputer Science (R0)