{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T07:17:27Z","timestamp":1758266247133,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539131","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:12Z","timestamp":1660331172000},"page":"4571-4581","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding"],"prefix":"10.1145","author":[{"given":"Wayne Xin","family":"Zhao","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"given":"Zheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"given":"Beichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"given":"Yuanhang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"given":"Jing","family":"Sha","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}]},{"given":"Zhigang","family":"Chen","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}]},{"given":"Shijin","family":"Wang","sequence":"additional","affiliation":[{"name":"AI Research (Central China), iFLYTEK, Wuhan, China"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research, Hefei, China"}]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"ICLR","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In ICLR 2015."},{"key":"e_1_3_2_2_2_1","volume-title":"Curriculum Learning. In ICML (ICML '09)","author":"Bengio Yoshua","year":"2009","unstructured":"Yoshua Bengio, J\u00e9r\u00f4me Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum Learning. In ICML (ICML '09)."},{"doi-asserted-by":"crossref","unstructured":"Ting-Rui Chiang and Yun-Nung Chen. 2019. Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems. In NAACL.","key":"e_1_3_2_2_3_1","DOI":"10.18653\/v1\/N19-1272"},{"key":"e_1_3_2_2_4_1","volume-title":"Pre-training with whole word masking for chinese bert. TASLP","author":"Cui Yiming","year":"2021","unstructured":"Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, and Ziqing Yang. 2021. Pre-training with whole word masking for chinese bert. TASLP (2021)."},{"key":"e_1_3_2_2_5_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_2_6_1","volume-title":"Instruments, & Computers","author":"Fletcher Charles R","year":"1985","unstructured":"Charles R Fletcher. 1985. Understanding and solving arithmetic word problems: A computer simulation. Behavior Research Methods, Instruments, & Computers (1985)."},{"doi-asserted-by":"crossref","unstructured":"Zheng Gong Kun Zhou Xin Zhao Jing Sha Shijin Wang and Ji-Rong Wen. 2022. Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network. In ACL. 5923--5933.","key":"e_1_3_2_2_7_1","DOI":"10.18653\/v1\/2022.acl-long.408"},{"key":"e_1_3_2_2_8_1","volume-title":"Smith","author":"Gururangan Suchin","year":"2020","unstructured":"Suchin Gururangan, Ana Marasovic, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In ACL."},{"key":"e_1_3_2_2_9_1","volume-title":"Learning achievement in solving word-based mathematical questions through a computer-assisted learning system","author":"Huang Tzu-Hua","year":"2012","unstructured":"Tzu-Hua Huang, Yuan-Chen Liu, and Hsiu-Chen Chang. 2012. Learning achievement in solving word-based mathematical questions through a computer-assisted learning system. Journal of Educational Technology & Society (2012)."},{"doi-asserted-by":"crossref","unstructured":"Chen Jia Yuefeng Shi Qinrong Yang and Yue Zhang. 2020. Entity Enhanced BERT Pre-training for Chinese NER. In EMNLP.","key":"e_1_3_2_2_10_1","DOI":"10.18653\/v1\/2020.emnlp-main.518"},{"volume-title":"Mathematical Ability","author":"Karsenty Ronnie","unstructured":"Ronnie Karsenty. 2014. Mathematical Ability. Springer Netherlands, Dordrecht.","key":"e_1_3_2_2_11_1"},{"doi-asserted-by":"crossref","unstructured":"Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. In EMNLP.","key":"e_1_3_2_2_12_1","DOI":"10.3115\/v1\/D14-1181"},{"doi-asserted-by":"crossref","unstructured":"Nate Kushman Yoav Artzi Luke Zettlemoyer and Regina Barzilay. 2014. Learning to automatically solve algebra word problems. In ACL.","key":"e_1_3_2_2_13_1","DOI":"10.3115\/v1\/P14-1026"},{"doi-asserted-by":"crossref","unstructured":"Siwei Lai Liheng Xu Kang Liu and Jun Zhao. 2015. Recurrent convolutional neural networks for text classification. In AAAI.","key":"e_1_3_2_2_14_1","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"e_1_3_2_2_15_1","volume-title":"Yan Wang, Dongxiang Zhang, and Ee-Peng Lim.","author":"Lan Yihuai","year":"2021","unstructured":"Yihuai Lan, Lei Wang, Qiyuan Zhang, Yunshi Lan, Bing Tian Dai, Yan Wang, Dongxiang Zhang, and Ee-Peng Lim. 2021. MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers. arXiv preprint arXiv:2109.00799 (2021)."},{"key":"e_1_3_2_2_16_1","volume-title":"The processes of student learning. Higher education 8, 4","author":"Laurillard Diana","year":"1979","unstructured":"Diana Laurillard. 1979. The processes of student learning. Higher education 8, 4 (1979), 395--409."},{"key":"e_1_3_2_2_17_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL.","author":"Lewis Mike","year":"2020","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In ACL."},{"key":"e_1_3_2_2_18_1","volume-title":"Bing Tian Dai, and Dongxiang Zhang","author":"Li Jierui","year":"2019","unstructured":"Jierui Li, Lei Wang, Jipeng Zhang, Yan Wang, Bing Tian Dai, and Dongxiang Zhang. 2019. Modeling intra-relation in math word problems with different functional multi-head attentions. In ACL."},{"key":"e_1_3_2_2_19_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In ACL","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In ACL 2004."},{"unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR.","key":"e_1_3_2_2_20_1"},{"doi-asserted-by":"crossref","unstructured":"Kishore Papineni Salim Roukos Todd Ward and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In ACL.","key":"e_1_3_2_2_21_1","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_22_1","volume-title":"MathBERT: A Pre-Trained Model for Mathematical Formula Understanding. arXiv preprint arXiv:2105.00377","author":"Peng Shuai","year":"2021","unstructured":"Shuai Peng, Ke Yuan, Liangcai Gao, and Zhi Tang. 2021. MathBERT: A Pre-Trained Model for Mathematical Formula Understanding. arXiv preprint arXiv:2105.00377 (2021)."},{"key":"e_1_3_2_2_23_1","volume-title":"Kunhao Zheng, Mantas Baksys, Igor Babuschkin, and Ilya Sutskever.","author":"Polu Stanislas","year":"2022","unstructured":"Stanislas Polu, Jesse Michael Han, Kunhao Zheng, Mantas Baksys, Igor Babuschkin, and Ilya Sutskever. 2022. Formal Mathematics Statement Curriculum Learning. arXiv:2202.01344 [cs.LG]"},{"key":"e_1_3_2_2_24_1","volume-title":"Generative language modeling for automated theorem proving. arXiv preprint arXiv:2009.03393","author":"Polu Stanislas","year":"2020","unstructured":"Stanislas Polu and Ilya Sutskever. 2020. Generative language modeling for automated theorem proving. arXiv preprint arXiv:2009.03393 (2020)."},{"key":"e_1_3_2_2_25_1","volume-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. JMLR","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. JMLR (2020)."},{"key":"e_1_3_2_2_26_1","volume-title":"A Primer in BERTology: What We Know About How BERT Works. TACL","author":"Rogers Anna","year":"2020","unstructured":"Anna Rogers, Olga Kovaleva, and Anna Rumshisky. 2020. A Primer in BERTology: What We Know About How BERT Works. TACL (2020)."},{"key":"e_1_3_2_2_27_1","volume-title":"CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. arXiv preprint arXiv:2109.05729","author":"Shao Yunfan","year":"2021","unstructured":"Yunfan Shao, Zhichao Geng, Yitao Liu, Junqi Dai, Fei Yang, Li Zhe, Hujun Bao, and Xipeng Qiu. 2021. CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation. arXiv preprint arXiv:2109.05729 (2021)."},{"key":"e_1_3_2_2_28_1","volume-title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education. arXiv preprint arXiv:2106.07340","author":"Shen Jia Tracy","year":"2021","unstructured":"Jia Tracy Shen, Michiharu Yamashita, Ethan Prihar, Neil Heffernan, Xintao Wu, Ben Graff, and Dongwon Lee. 2021. MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education. arXiv preprint arXiv:2106.07340 (2021)."},{"doi-asserted-by":"crossref","unstructured":"Shuming Shi Yuehui Wang Chin-Yew Lin Xiaojiang Liu and Yong Rui. 2015. Automatically solving number word problems by semantic parsing and reasoning. In EMNLP. 1132--1142.","key":"e_1_3_2_2_29_1","DOI":"10.18653\/v1\/D15-1135"},{"doi-asserted-by":"crossref","unstructured":"Yujin Song and Xiaoyu Chen. 2021. Searching for Mathematical Formulas Based on Graph Representation Learning. In CICM.","key":"e_1_3_2_2_30_1","DOI":"10.1007\/978-3-030-81097-9_11"},{"key":"e_1_3_2_2_31_1","volume-title":"Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation. CoRR","author":"Sun Yu","year":"2021","unstructured":"Yu Sun, Shuohuan Wang, Shikun Feng, Siyu Ding, Chao Pang, Junyuan Shang, Jiaxiang Liu, Xuyi Chen, Yanbin Zhao, Yuxiang Lu, Weixin Liu, Zhihua Wu, Weibao Gong, Jianzhong Liang, Zhizhou Shang, Peng Sun, Wei Liu, Xuan Ouyang, Dianhai Yu, Hao Tian, Hua Wu, and Haifeng Wang. 2021. ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation. CoRR (2021)."},{"doi-asserted-by":"crossref","unstructured":"Zijun Sun Xiaoya Li Xiaofei Sun Yuxian Meng Xiang Ao Qing He Fei Wu and Jiwei Li. 2021. ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information. In ACL.","key":"e_1_3_2_2_32_1","DOI":"10.18653\/v1\/2021.acl-long.161"},{"unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.","key":"e_1_3_2_2_33_1"},{"doi-asserted-by":"crossref","unstructured":"Yan Wang Xiaojiang Liu and Shuming Shi. 2017. Deep neural solver for math word problems. In EMNLP.","key":"e_1_3_2_2_34_1","DOI":"10.18653\/v1\/D17-1088"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_35_1","DOI":"10.1007\/s10032-011-0174-4"},{"unstructured":"Wei Zeng Xiaozhe Ren Teng Su Hui Wang Yi Liao Zhiwei Wang Xin Jiang ZhenZhang Yang Kaisheng Wang Xiaoda Zhang et al. 2021. PanGu-a: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation. arXiv preprint arXiv:2104.12369 (2021).","key":"e_1_3_2_2_36_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_37_1","DOI":"10.1016\/j.aiopen.2021.07.001"},{"key":"e_1_3_2_2_38_1","volume-title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese. arXiv preprint arXiv:2110.06696","author":"Zhang Zhuosheng","year":"2021","unstructured":"Zhuosheng Zhang, Hanqing Zhang, Keming Chen, Yuhang Guo, Jingyun Hua, Yulong Wang, and Ming Zhou. 2021. Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese. arXiv preprint arXiv:2110.06696 (2021)."}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"acronym":"KDD '22","name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA"},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539131","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:58Z","timestamp":1750186978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":38,"alternative-id":["10.1145\/3534678.3539131","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539131","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}