Abstract
The mainstream textual entailment recognition models ignore the existing language knowledge, so the inference knowledge from the training data is limited, and the generalization ability is not strong. Therefore, this paper proposes a model KBRTE (fusing Knowledge Base in RTE) that combines an attention mechanism and a pre-trained model and uses word vectors based on sememe representation in the HowNet. We use the enhanced CNLI and XNLI datasets as the model’s training set. On the basis of these datasets, monosemous and polysemous in the CiLin are integrated to further enhance the knowledge. Experimental results show that this method could bring significant gains.
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
Lan, W., Xu, W.: Neural network models for paraphrase identification, semantic textual similarity, natural language inference, and question answering. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3890–3902 (2018)
Li, S., Li H., Zhao Q.: Chinese textual entailment recognition fused with external semantic knowledge. Comput. Eng. 47(1), 44–49 (2021). https://doi.org/10.19678/j.issn.1000-3428.0056841
Miller, George, A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Dong, Z., Dong, Q.: HowNet - a hybrid language and knowledge resource. In: International Conference on Natural Language Processing and Knowledge Engineering, pp. 820–824 (2003)
Mei, J., Zhu, Y., Gao, Y.: TongYiCi CiLin.: Shanghai Lexicographical Publishing House (1983)
Liu, Y., Mu, L., Zan, H.: A deep learning model fused with word sense knowledge for textual entailment recognition. In: International Conference on Asian Language Processing (IALP), pp. 189–194. IEEE (2021)
Parikh, A., Tckstrm, O., Uszkoreit, J.: A decomposable attention model for natural language inference. arXiv preprint arXiv:1606.01933 (2016)
Chen, Q., Zhu, X., Ling, Z.: Enhanced LSTM for natural language inference. arXiv preprint arXiv:1609.06038 (2016)
Hu, C., Wu, C., Yang, Y.: Extended S-LSTM based textual entailment recognition. J. Comput. Res. Develop. 57(7), 1481–1489 (2020)
Huang, S., Xiao, S., Du, Y.: Chinese textual entailment recognition method based on hybrid attention. J. Beijing Univ. Inf. Technol. 35(3), 89–93.98 (2020). https://doi.org/10.16508/j.cnki.11-5866/n.2020.03.017
Devlin, J., Chang, M., Lee, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Cui, Y., Che, W., Liu, T.: Pre-training with whole word masking for Chinese BERT. IEEE/ACM Trans. Audio Speech Lang. Process, 29, 3504–3514 (2021)
Liu, X., He, P., Chen, W.: Multi-task deep neural networks for natural language understanding. arXiv preprint arXiv:1901.11504 (2019)
Conneau, A., Khandelwal, K., Goyal, N.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)
Artetxe, M., Ruder, S., Yogatama, D.: On the cross-lingual transferability of monolingual representations. arXiv preprint arXiv:1911.02116 (2019)
Qian, C., Zhu, X., Ling, Z.: Neural natural language inference models enhanced with external knowledge. arXiv preprint arXiv:1711.04289 (2017)
Niu, Y., Xie, R., Liu, Z.: IMproved word representation learning with sememes. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 2049–2058 (2017)
Yu, Q., Wang, B., Liu, M.: A fine-tuning method based on Tongyi CiLin and pre-trained word embedding. Chinese J. Inf. 34(10), 27–32 (2020)
Zhang, Z., Zeng, Y., Pang, Y.: A Chinese textual entailment recognition method incorporating semantic role and self-attention. J. Electron. 48(11), 2162–2169 (2020)
Wang, H.: Text entailment recognition based on integration of language knowledge and deep learning and its application. Harbin Institute of Technology (2019)
Acknowledgment
We are very grateful to the anonymous reviewers for their constructive opinions, the Science and Technique Program of Henan Province under Grant No. 192102210260, and the Teaching Reform Program of Zhengzhou University under Grant No. 2021ZZUJGLX131.
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, Y., Mu, L., Zan, H. (2022). KBRTE: A Deep Learning Model for Chinese Textual Entailment Recognition Based on Synonym Expansion and Sememe Enhancement. In: Lu, W., Huang, S., Hong, Y., Zhou, X. (eds) Natural Language Processing and Chinese Computing. NLPCC 2022. Lecture Notes in Computer Science(), vol 13551. Springer, Cham. https://doi.org/10.1007/978-3-031-17120-8_59
Download citation
DOI: https://doi.org/10.1007/978-3-031-17120-8_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17119-2
Online ISBN: 978-3-031-17120-8
eBook Packages: Computer ScienceComputer Science (R0)
