{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T03:13:02Z","timestamp":1772507582538,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Pengpeng Jian","award":["No. 62107014"],"award-info":[{"award-number":["No. 62107014"]}]},{"name":"Yangrui Yang","award":["25A520006"],"award-info":[{"award-number":["25A520006"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Math Word Problems (MWP) solving involves language comprehension and mathematical reasoning. Most of the existing models are primarily based on deep learning methods. However, deep learning models often exhibit large model scales (e.g., large number of parameters), high feature dimensions, and an imbalance between accuracy and computational efficiency. To address these issues, We propose a novel dual-decoder model for solving Mathematical Word Problems (MWP), which is constructed using a Lie Group intrinsic mean feature matrix and named the Dual-Decoder Neural Symbolic Machine (DDNSM). This model projects data samples onto a Lie Group manifold to effectively reduce the output feature dimensions of the encoder through a feature matrix built around the Lie Group intrinsic mean, thereby reducing the computational load in the decoding stage and improving model inference efficiency. Additionally, we designed a dual-decoder system, comprising a decoder based on global and local attention mechanisms and another structured around a tree built from the Lie Group intrinsic mean. Extensive experiments on multiple challenging public datasets demonstrate that our model achieves competitive results in MWP tasks, achieving competitive results in MWP tasks with improved accuracy and computational efficiency.<\/jats:p>","DOI":"10.1007\/s11063-025-11804-3","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T08:53:03Z","timestamp":1759740783000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Dual Decoder Mathematical Word Problem Solving Model Based on Lie Group Intrinsic Mean Feature Matrix"],"prefix":"10.1007","volume":"57","author":[{"given":"Pengpeng","family":"Jian","sequence":"first","affiliation":[]},{"given":"Tianhao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Xi","sequence":"additional","affiliation":[]},{"given":"Yangrui","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"key":"11804_CR1","doi-asserted-by":"crossref","unstructured":"Arnau-Gonz\u00e1lez P, Serrano-Mamolar A, Katsigiannis S, Althobaiti T, Arevalillo-Herr\u00e1ez M (2023) Towards automatic tutoring of math word problems in intelligent tutoring systems. IEEE Access","DOI":"10.1109\/ACCESS.2023.3290478"},{"issue":"9","key":"11804_CR2","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1109\/TPAMI.2019.2914054","volume":"42","author":"D Zhang","year":"2019","unstructured":"Zhang D, Wang L, Zhang L, Dai BT, Shen HT (2019) The gap of semantic parsing: A survey on automatic math word problem solvers. IEEE Trans Pattern Anal Mach Intell 42(9):2287\u20132305","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11804_CR3","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TASLP.2022.3145314","volume":"30","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Zhou G, Xie Z, Huang JX (2022) Hgen: Learning hierarchical heterogeneous graph encoding for math word problem solving. IEEE\/ACM Transactions on Audio Speech and Language Processing 30:816\u2013828","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"11804_CR4","doi-asserted-by":"crossref","unstructured":"Huang D, Shi S, Lin C-Y, Yin J (2017) Learning fine-grained expressions to solve math word problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 805\u2013814","DOI":"10.18653\/v1\/D17-1084"},{"issue":"5","key":"11804_CR5","doi-asserted-by":"publisher","first-page":"565","DOI":"10.3758\/BF03207654","volume":"17","author":"CR Fletcher","year":"1985","unstructured":"Fletcher CR (1985) Understanding and solving arithmetic word problems: A computer simulation. Behavior Research Methods Instruments & Computers 17(5):565\u2013571","journal-title":"Behavior Research Methods Instruments & Computers"},{"key":"11804_CR6","unstructured":"Bakman Y (2007) Robust understanding of word problems with extraneous information. arXiv preprint math\/0701393"},{"key":"11804_CR7","doi-asserted-by":"crossref","unstructured":"Shi S, Wang Y, Lin C-Y, Liu X, Rui Y (2015) Automatically solving number word problems by semantic parsing and reasoning. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1132\u20131142","DOI":"10.18653\/v1\/D15-1135"},{"key":"11804_CR8","unstructured":"Charniak E (1969) Computer solution of calculus word problems. In: Proceedings of the 1st International Joint Conference on Artificial Intelligence, pp. 303\u2013316"},{"key":"11804_CR9","doi-asserted-by":"crossref","unstructured":"Liu Q, Guan W, Li S, Kawahara D (2019) Tree-structured decoding for solving math word problems. 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. 2370\u20132379","DOI":"10.18653\/v1\/D19-1241"},{"key":"11804_CR10","doi-asserted-by":"crossref","unstructured":"Kushman N, Artzi Y, Zettlemoyer L, Barzilay R (2014) Learning to automatically solve algebra word problems. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 271\u2013281","DOI":"10.3115\/v1\/P14-1026"},{"key":"11804_CR11","doi-asserted-by":"crossref","unstructured":"Zhou L, Dai S, Chen L (2015) Learn to solve algebra word problems using quadratic programming. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 817\u2013822","DOI":"10.18653\/v1\/D15-1096"},{"key":"11804_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114704","volume":"174","author":"K Zaporojets","year":"2021","unstructured":"Zaporojets K, Bekoulis G, Deleu J, Demeester T, Develder C (2021) Solving arithmetic word problems by scoring equations with recursive neural networks. Expert Syst Appl 174:114704","journal-title":"Expert Syst Appl"},{"key":"11804_CR13","doi-asserted-by":"crossref","unstructured":"Wang Y, Liu X, Shi S (2017) Deep neural solver for math word problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 845\u2013854","DOI":"10.18653\/v1\/D17-1088"},{"key":"11804_CR14","doi-asserted-by":"crossref","unstructured":"Zhang J, Wang L, Lee RK-W, Bin Y, Wang Y, Shao J, Lim E-P (2020) Graph-to-tree learning for solving math word problems. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3928\u20133937","DOI":"10.18653\/v1\/2020.acl-main.362"},{"key":"11804_CR15","unstructured":"Vaswani A (2017) Attention is all you need. Advances in Neural Information Processing Systems"},{"key":"11804_CR16","unstructured":"Faldu K, Sheth A, Kikani P, Patel D (2022) Mmtm: Multi-tasking multi-decoder transformer for math word problems. arXiv preprint arXiv:2206.01268"},{"key":"11804_CR17","unstructured":"Hu Z, Jiang M (2022) Heterogeneous line graph transformer for math word problems. arXiv preprint arXiv:2208.05645"},{"key":"11804_CR18","unstructured":"Liu Y (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"11804_CR19","doi-asserted-by":"crossref","unstructured":"Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional lstm networks. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., vol. 4, pp. 2047\u20132052. IEEE","DOI":"10.1109\/IJCNN.2005.1556215"},{"issue":"10","key":"11804_CR20","doi-asserted-by":"publisher","first-page":"1741","DOI":"10.1109\/LGRS.2020.3007775","volume":"18","author":"C Xu","year":"2020","unstructured":"Xu C, Zhu G, Shu J (2020) A lightweight intrinsic mean for remote sensing classification with lie group kernel function. IEEE Geosci Remote Sens Lett 18(10):1741\u20131745","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"5","key":"11804_CR21","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/LGRS.2020.2986779","volume":"18","author":"C Xu","year":"2020","unstructured":"Xu C, Zhu G, Shu J (2020) Robust joint representation of intrinsic mean and kernel function of lie group for remote sensing scene classification. IEEE Geosci Remote Sens Lett 18(5):796\u2013800","journal-title":"IEEE Geosci Remote Sens Lett"},{"issue":"6","key":"11804_CR22","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.3390\/rs14061445","volume":"14","author":"C Xu","year":"2022","unstructured":"Xu C, Zhu G, Shu J (2022) A combination of lie group machine learning and deep learning for remote sensing scene classification using multi-layer heterogeneous feature extraction and fusion. Remote Sensing 14(6):1445","journal-title":"Remote Sensing"},{"key":"11804_CR23","doi-asserted-by":"publisher","unstructured":"Shu J, Wang Z, Wang J (2024) A scene classification model based on global-local features and attention in lie group space. Remote Sens 16(13):2323. https:\/\/doi.org\/10.3390\/rs16132323","DOI":"10.3390\/rs16132323"},{"key":"11804_CR24","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11804_CR25","doi-asserted-by":"publisher","unstructured":"ZHANG J, LEE RK-W, LIM E-P, QIN W, WANG L, SHAO J, SUN Q (2020) Teacher-student networks with multiple decoders for solving math word problem. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence 2020: Yokohama, 4011\u20134017 https:\/\/doi.org\/10.24963\/ijcai.2020\/555","DOI":"10.24963\/ijcai.2020\/555"},{"key":"11804_CR26","doi-asserted-by":"crossref","unstructured":"Apostolidis E, Balaouras G, Mezaris V, Patras I (2021) Combining global and local attention with positional encoding for video summarization. In: 2021 IEEE International Symposium on Multimedia (ISM), pp. 226\u2013234. IEEE","DOI":"10.1109\/ISM52913.2021.00045"},{"key":"11804_CR27","doi-asserted-by":"crossref","unstructured":"Xie Z, Sun S (2019) A goal-driven tree-structured neural model for math word problems. In: Ijcai, pp. 5299\u20135305","DOI":"10.24963\/ijcai.2019\/736"},{"key":"11804_CR28","doi-asserted-by":"crossref","unstructured":"Tan M, Wang L, Jiang L, Jiang J (2021) Investigating math word problems using pretrained multilingual language models. arXiv preprint arXiv:2105.08928","DOI":"10.18653\/v1\/2022.mathnlp-1.2"},{"key":"11804_CR29","unstructured":"Zhao W, Shang M, Liu Y, Wang L, Liu J (2020) Ape210k: A large-scale and template-rich dataset of math word problems. arXiv preprint arXiv:2009.11506"},{"key":"11804_CR30","unstructured":"Hensman P, Masko D (2015) The impact of imbalanced training data for convolutional neural networks. Degree Project in Computer Science, KTH Royal Institute of Technology"},{"key":"11804_CR31","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u2013893. Ieee","DOI":"10.1109\/CVPR.2005.177"},{"issue":"7553","key":"11804_CR32","first-page":"436","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning nature 521(7553):436\u2013444","journal-title":"Deep learning nature"},{"key":"11804_CR33","doi-asserted-by":"crossref","unstructured":"Wang L, Wang Y, Cai D, Zhang D, Liu X (2018) Translating a math word problem to an expression tree. arXiv preprint arXiv:1811.05632","DOI":"10.18653\/v1\/D18-1132"},{"key":"11804_CR34","doi-asserted-by":"crossref","unstructured":"Qin J, Lin L, Liang X, Zhang R, Lin L (2020) Semantically-aligned universal tree-structured solver for math word problems. arXiv preprint arXiv:2010.06823","DOI":"10.18653\/v1\/2020.emnlp-main.309"},{"key":"11804_CR35","doi-asserted-by":"crossref","unstructured":"Qin J, Liang X, Hong Y, Tang J, Lin L (2021) Neural-symbolic solver for math word problems with auxiliary tasks. arXiv preprint arXiv:2107.01431","DOI":"10.18653\/v1\/2021.acl-long.456"},{"key":"11804_CR36","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907"},{"key":"11804_CR37","doi-asserted-by":"crossref","unstructured":"Li S, Wu L, Feng S, Xu F, Xu F, Zhong S (2020) Graph-to-tree neural networks for learning structured input-output translation with applications to semantic parsing and math word problem. arXiv preprint arXiv:2004.13781","DOI":"10.18653\/v1\/2020.findings-emnlp.255"},{"key":"11804_CR38","doi-asserted-by":"crossref","unstructured":"Huang S, Wang J, Xu J, Cao D, Yang M (2021) Recall and learn: A memory-augmented solver for math word problems. arXiv preprint arXiv:2109.13112","DOI":"10.18653\/v1\/2021.findings-emnlp.68"},{"issue":"4","key":"11804_CR39","doi-asserted-by":"publisher","first-page":"916","DOI":"10.3390\/sym15040916","volume":"15","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Zhang T, Xie P, Yu M, Yu G (2023) Bem-sm: A bert-encoder model with symmetry supervision module for solving math word problem. Symmetry 15(4):916","journal-title":"Symmetry"},{"issue":"2","key":"11804_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103585","volume":"61","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Zhou G, Xie Z, Huang JX (2024) Number-enhanced representation with hierarchical recursive tree decoding for math word problem solving. Information Processing & Management 61(2):103585","journal-title":"Information Processing & Management"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11804-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-025-11804-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-025-11804-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T04:43:47Z","timestamp":1760762627000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-025-11804-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":40,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["11804"],"URL":"https:\/\/doi.org\/10.1007\/s11063-025-11804-3","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"25 August 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"85"}}