{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:09:24Z","timestamp":1760058564450,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T00:00:00Z","timestamp":1744329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Intelligent Integrated Media Platform R&amp;D and Application Demonstration Project","award":["PM21014X"],"award-info":[{"award-number":["PM21014X"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Aiming at the problems of noise interference and the lack of information on sentence\u2013subject interactions in Chinese matching models, which lead to their low accuracy, a new semantic matching method using fine-grained context features and sentence\u2013subject interaction is designed. Compared with the method that relies on noisy data to improve the noise resistance of the model, we introduce data pollution and imprecise noise processing. We also design a novel context refinement strategy, which uses dot product attention, a gradient reversal layer, the Softmax function, and projection theorem to accurately identify and eliminate noise features to obtain high-quality refined context features, effectively overcoming the above shortcomings. Then, we innovatively use a one-way interaction strategy based on the projection theorem to map the sentence subject to the refined context feature space, which produces effective interaction ability between the features in the model. The refined context and sentence\u2019s main idea are fused in the final prediction stage to compute the matching result. In addition, this study uses Kullback\u2013Leibler divergence scatter to optimize the distance between the distributions of the refined context and the sentence\u2019s main idea so that their distributions are closer to each other. The experimental results show that the accuracy of the method on the PAWS dataset and F1 are 87.65% and 86.51%, respectively; 80.51% on the Ant Financial dataset, and 85.29% on the BQ dataset. The accuracies on the Medic-SM dataset and Macro-F1 are 74.69% and 74% respectively, both of which are superior to those of other methods.<\/jats:p>","DOI":"10.3390\/sym17040585","type":"journal-article","created":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T06:45:31Z","timestamp":1744353931000},"page":"585","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Matching for Chinese Language Approach Using Refined Contextual Features and Sentence\u2013Subject Interaction"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4938-6245","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China"}]},{"given":"Xiaodong","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3105","DOI":"10.1007\/s13042-023-01823-8","article-title":"Text Semantic Matching with an Enhanced Sample Building Method Based on Contrastive Learning","volume":"14","author":"Wu","year":"2023","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Jin, Z.L., Hong, Y., Peng, R., Yao, J.M., and Zhou, G.D. (2023, January 2\u20136). Intention-Aware Neural Networks for Question Paraphrase Identification. Proceedings of the 45th European Conference on Information Retrieval, Dublin, Ireland.","DOI":"10.1007\/978-3-031-28244-7_30"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"101575","DOI":"10.1016\/j.csl.2023.101575","article-title":"M-Sim: Multi-Level Semantic Inference Model for Chinese Short Answer Scoring in Low-Resource Scenarios","volume":"84","author":"Lai","year":"2024","journal-title":"Comput. Speech Lang."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Neeman, E., Aharoni, R., Honovich, O., Choshen, L., Szpektor, I., and Abend, O. (2022). Disentqa: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering. arXiv.","DOI":"10.18653\/v1\/2023.acl-long.559"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"15632","DOI":"10.1007\/s10489-022-03410-w","article-title":"Short Text Matching Model with Multiway Semantic Interaction Based on Multi-Granularity Semantic Embedding","volume":"52","author":"Tang","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"103320","DOI":"10.1016\/j.ipm.2023.103320","article-title":"CNN-BiLSTM-Attention: A Multi-Label Neural Classifier for Short Texts with a Small Set of Labels","volume":"60","author":"Lu","year":"2023","journal-title":"Inf. Process. Manag."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Jiang, K., Zhao, Y., Jin, G., Zhang, Z., and Cui, R. (2023). KETM: A Knowledge-Enhanced Text Matching Method, IEEE.","DOI":"10.1109\/IJCNN54540.2023.10191337"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102738","DOI":"10.1016\/j.ipm.2021.102738","article-title":"A Simple and Efficient Text Matching Model Based on Deep Interaction","volume":"58","author":"Yu","year":"2021","journal-title":"Inf. Process. Manag."},{"key":"ref_9","unstructured":"Li, Y. (2023). Unlocking Context Constraints of Llms: Enhancing Context Efficiency of Llms with Self-Information-Based Content Filtering. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhao, J., Zhan, W., Zhao, X., Zhang, Q., Gui, T., Wei, Z., Wang, J., Peng, M., and Sun, M. (2023). RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction. arXiv.","DOI":"10.18653\/v1\/2023.acl-long.369"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zou, Y., Liu, H., Gui, T., Wang, J., Zhang, Q., Tang, M., Li, H., Wang, D., and Assoc Computa, L. (2022). Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents. arXiv.","DOI":"10.18653\/v1\/2022.findings-acl.287"},{"key":"ref_12","first-page":"12084","article-title":"Improved Feature Distillation via Projector Ensemble","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_13","unstructured":"Snell, C., Klein, D., and Zhong, R. (2022). Learning by Distilling Context. arXiv."},{"key":"ref_14","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., and Choi, J.Y. (November, January 27). A Comprehensive Overhaul of Feature Distillation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, Z., Hamza, W., and Florian, R. (2017). Bilateral Multi-Perspective Matching for Natural Language Sentences. arXiv.","DOI":"10.24963\/ijcai.2017\/579"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. arXiv.","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref_17","unstructured":"Bulsari, A.B., and Saxen, H. (1992, January 4\u20137). A RECURRENT NEURAL NETWORK MODEL. Proceedings of the 1992 International Conference (ICANN-92), Brighton, UK."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wu, L., Lv, G.Y., Wang, M., Chen, E.H., and Ruan, S.L. (2021, January 2\u20139). Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, Online.","DOI":"10.1609\/aaai.v35i16.17694"},{"key":"ref_19","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2018). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. arXiv."},{"key":"ref_20","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A Robustly Optimized Bert Pretraining Approach. arXiv."},{"key":"ref_21","unstructured":"Yao, D., Alghamdi, A., Xia, Q., Qu, X., Duan, X., Wang, Z., Zheng, Y., Huai, B., Cheng, P., and Zhao, Z. (2024). A General and Flexible Multi-Concept Parsing Framework for Multilingual Semantic Matching. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103576","DOI":"10.1016\/j.ipm.2023.103576","article-title":"STMAP: A Novel Semantic Text Matching Model Augmented with Embedding Perturbations","volume":"61","author":"Wang","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"ref_23","unstructured":"Ganin, Y., and Lempitsky, V. (2015, January 6\u201311). Unsupervised Domain Adaptation by Backpropagation. Proceedings of the 32nd International Conference on Machine Learning, Lille, France."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1080\/00927878408823034","article-title":"Fundamental Theorem of Projective Geometry","volume":"12","author":"Sarath","year":"1984","journal-title":"Commun. Algebra"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lin, J., Zou, J., and Ding, N. (2021). Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models. arXiv.","DOI":"10.18653\/v1\/2021.acl-short.43"},{"key":"ref_26","unstructured":"Manjunatha, V., Saini, N., and Davis, L.S. (November, January 27). Explicit Bias Discovery in Visual Question Answering Models. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_27","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled Weight Decay Regularization. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3504","DOI":"10.1109\/TASLP.2021.3124365","article-title":"Pre-Training with Whole Word Masking for Chinese Bert","volume":"29","author":"Cui","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2800","DOI":"10.1109\/TASLP.2024.3402087","article-title":"CoSENT: Consistent Sentence Embedding via Similarity Ranking","volume":"32","author":"Huang","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/585\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:12:48Z","timestamp":1760029968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,11]]},"references-count":29,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["sym17040585"],"URL":"https:\/\/doi.org\/10.3390\/sym17040585","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,4,11]]}}}