{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T17:46:10Z","timestamp":1794851170296,"version":"4.9.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032360328","type":"print"},{"value":"9783032360335","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T00:00:00Z","timestamp":1787443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-36033-5_8","type":"book-chapter","created":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:24Z","timestamp":1787404884000},"page":"126-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GSMP: Geometry-Structured Masked Pre-training with\u00a0Multi-granularity Objectives and\u00a0Curriculum Learning for\u00a0Geometric Problem Solving"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1314-5629","authenticated-orcid":false,"given":"Ziming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0757-8491","authenticated-orcid":false,"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingxiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0952-1686","authenticated-orcid":false,"given":"Minzhi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2773-3150","authenticated-orcid":false,"given":"Zhi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5513-1192","authenticated-orcid":false,"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8061-1474","authenticated-orcid":false,"given":"Xiangdong","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,23]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Amini, A., Gabriel, S., Lin, S., Koncel-Kedziorski, R., Choi, Y., Hajishirzi, H.: Mathqa: towards interpretable math word problem solving with operation-based formalisms. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 2357\u20132367 (2019)","DOI":"10.18653\/v1\/N19-1245"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Beck, D., Haffari, G., Cohn, T.: Graph-to-sequence learning using gated graph neural networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 273\u2013283 (2018)","DOI":"10.18653\/v1\/P18-1026"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41\u201348 (2009)","DOI":"10.1145\/1553374.1553380"},{"key":"8_CR5","unstructured":"Cao, J., Xiao, J.: An augmented benchmark dataset for geometric question answering through dual parallel text encoding. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 1511\u20131520 (2022)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Unigeo: Unifying geometry logical reasoning via reformulating mathematical expression. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3313\u20133323 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Geoqa: a geometric question answering benchmark towards multimodal numerical reasoning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 513\u2013523 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: Uniter: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"8_CR9","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: International Conference on Machine Learning, pp. 1931\u20131942. PMLR (2021)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Hao, Y., Zhang, M., Yin, F., Huang, L.L.: Pgdp5k: a diagram parsing dataset for plane geometry problems. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1763\u20131769. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956397"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"8_CR14","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"8_CR16","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z.Z., Zhang, M.L., Yin, F., Liu, C.L.: Lans: a layout-aware neural solver for plane geometry problem. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 2596\u20132608 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.153"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Liang, Z., et al.: Mwp-bert: numeracy-augmented pre-training for math word problem solving. In: Findings of the Association for Computational Linguistics: NAACL 2022, pp. 997\u20131009 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.74"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., He, P., Chen, W., Gao, J.: Multi-task deep neural networks for natural language understanding. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4487\u20134496 (2019)","DOI":"10.18653\/v1\/P19-1441"},{"key":"8_CR20","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Inter-gps: interpretable geometry problem solving with formal language and symbolic reasoning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 6774\u20136786 (2021)","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"8_CR22","unstructured":"Lu, P., et al.: Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning. arXiv preprint arXiv:2209.14610 (2022)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Lu, P., Qiu, L., Yu, W., Welleck, S., Chang, K.W.: A survey of deep learning for mathematical reasoning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (volume 1: long papers), pp. 14605\u201314631 (2023)","DOI":"10.18653\/v1\/2023.acl-long.817"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Patel, A., Bhattamishra, S., Goyal, N.: Are NLP models really able to solve simple math word problems? In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2080\u20132094 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Sachan, M., Dubey, K., Xing, E.: From textbooks to knowledge: a case study in harvesting axiomatic knowledge from textbooks to solve geometry problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 773\u2013784 (2017)","DOI":"10.18653\/v1\/D17-1081"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Seo, M., Hajishirzi, H., Farhadi, A., Etzioni, O., Malcolm, C.: Solving geometry problems: Combining text and diagram interpretation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1466\u20131476 (2015)","DOI":"10.18653\/v1\/D15-1171"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Tsai, S., Liang, C., Wang, H., Su, K.: Sequence to general tree: Knowledge-guided geometry word problem solving. arxiv 2021. arXiv preprint arXiv:2106.00990","DOI":"10.18653\/v1\/2021.acl-short.121"},{"key":"8_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"issue":"9","key":"8_CR29","first-page":"4555","volume":"44","author":"X Wang","year":"2021","unstructured":"Wang, X., Chen, Y., Zhu, W.: A survey on curriculum learning. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 4555\u20134576 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liu, X., Shi, S.: Deep neural solver for math word problems. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 845\u2013854 (2017)","DOI":"10.18653\/v1\/D17-1088"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Xie, Z., Sun, S.: A goal-driven tree-structured neural model for math word problems. In: IJCAI, pp, 5299\u20135305 (2019)","DOI":"10.24963\/ijcai.2019\/736"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Xu, B., Zhang, L., Mao, Z., Wang, Q., Xie, H., Zhang, Y.: Curriculum learning for natural language understanding. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 6095\u20136104 (2020)","DOI":"10.18653\/v1\/2020.acl-main.542"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, M., Cui, L., Huang, S., Wei, F., Zhou, M.: Layoutlm: pre-training of text and layout for document image understanding. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1192\u20131200 (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7370\u20137377 (2019)","DOI":"10.1609\/aaai.v33i01.33017370"},{"key":"8_CR35","doi-asserted-by":"publisher","first-page":"12647","DOI":"10.52202\/068431-0919","volume":"35","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Moshfeghi, Y.: Elastic: numerical reasoning with adaptive symbolic compiler. Adv. Neural. Inf. Process. Syst. 35, 12647\u201312661 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, M.L., Yin, F., Hao, Y.H., Liu, C.L.: Plane geometry diagram parsing. arXiv preprint arXiv:2205.09363 (2022)","DOI":"10.24963\/ijcai.2022\/228"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, M.L., Yin, F., Liu, C.L.: A multi-modal neural geometric solver with textual clauses parsed from diagram. arXiv preprint arXiv:2302.11097 (2023)","DOI":"10.24963\/ijcai.2023\/376"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, X., Liu, Z., Jiang, X., Sun, M., Liu, Q.: Ernie: enhanced language representation with informative entities. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1441\u20131451 (2019)","DOI":"10.18653\/v1\/P19-1139"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36033-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T13:21:33Z","timestamp":1787404893000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36033-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,23]]},"ISBN":["9783032360328","9783032360335"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36033-5_8","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-36033-5","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,23]]},"assertion":[{"value":"23 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vienna","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Austria","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}