{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:13:18Z","timestamp":1785838398637,"version":"3.56.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T00:00:00Z","timestamp":1604793600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T00:00:00Z","timestamp":1604793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1007\/s10032-020-00360-2","type":"journal-article","created":{"date-parts":[[2020,11,8]],"date-time":"2020-11-08T14:02:33Z","timestamp":1604844153000},"page":"63-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Translating math formula images to LaTeX sequences using deep neural networks with sequence-level training"],"prefix":"10.1007","volume":"24","author":[{"given":"Zelun","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1330-5092","authenticated-orcid":false,"given":"Jyh-Charn","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,8]]},"reference":[{"key":"360_CR1","unstructured":"Ion, P., Miner, R., Buswell, S., Devitt, A.: Mathematical Markup Language (MathML) 1.0 Specification. World Wide Web Consortium (W3C) (1998)"},{"key":"360_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, R.H.: Syntax-directed recognition of hand-printed two-dimensional mathematics. In: Symposium on Interactive Systems for Experimental Applied Mathematics: Proceedings of the Association for Computing Machinery Inc. Symposium, pp. 436\u2013459. ACM (1967)","DOI":"10.1016\/B978-0-12-395608-8.50048-7"},{"key":"360_CR3","doi-asserted-by":"crossref","unstructured":"Suzuki, M., Tamari, F., Fukuda, R., Uchida, S., Kanahori, T.: INFTY: an integrated OCR system for mathematical documents. In: Proceedings of the 2003 ACM Symposium on Document Engineering, pp. 95\u2013104. ACM (2003)","DOI":"10.1145\/958220.958239"},{"key":"360_CR4","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Deep structured output learning for unconstrained text recognition (2014). arXiv preprint arXiv:1412.5903"},{"key":"360_CR5","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"360_CR6","unstructured":"Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhudinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"360_CR7","unstructured":"Deng, Y., Kanervisto, A., Rush, A.M.: What you get is what you see: a visual markup decompiler, vol. 10, pp. 32\u201337 (2016). arXiv preprint arXiv:1609.04938"},{"key":"360_CR8","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"360_CR9","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S. P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)."},{"key":"360_CR10","unstructured":"Ranzato, M.A., Chopra, S., Auli, M., Zaremba, W.: Sequence level training with recurrent neural networks (2015). arXiv preprint arXiv:1511.06732"},{"issue":"1","key":"360_CR11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/PL00013549","volume":"3","author":"K-F Chan","year":"2000","unstructured":"Chan, K.-F., Yeung, D.-Y.: Mathematical expression recognition: a survey. Int. J. Doc. Anal. Recogn. 3(1), 3\u201315 (2000)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"360_CR12","doi-asserted-by":"crossref","unstructured":"Garain, U., Chaudhuri, B., Chaudhuri, A.R.: Identification of embedded mathematical expressions in scanned documents. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, vol. 1, pp. 384\u2013387. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334132"},{"key":"360_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Beyette, D., Lin, J., Liu, J.-C.: Extraction of math expressions from PDF documents based on unsupervised modeling of fonts. In: IAPR International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia. IEEE (2019).","DOI":"10.1109\/ICDAR.2019.00068"},{"key":"360_CR14","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Z., Liu, J.-C.: Bigram label regularization to reduce over-segmentation on inline math expression detection. In: IAPR International Conference on Document Analysis and Recognition (ICDAR), Sydney, Australia. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00069"},{"key":"360_CR15","doi-asserted-by":"crossref","unstructured":"Gao, L., Yi, X., Liao, Y., Jiang, Z., Yan, Z., Tang, Z.: A deep learning-based formula detection method for PDF documents. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), pp. 553\u2013558. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.96"},{"key":"360_CR16","doi-asserted-by":"crossref","unstructured":"Twaakyondo, H.M., Okamoto, M.: Structure analysis and recognition of mathematical expressions. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 1, pp. 430\u2013437. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.599029"},{"key":"360_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)."},{"key":"360_CR18","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"360_CR19","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 3304\u20133308. IEEE (2012)"},{"issue":"11","key":"360_CR20","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"360_CR21","doi-asserted-by":"crossref","unstructured":"Luong, M.-T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation (2015). arXiv preprint arXiv:1508.04025","DOI":"10.18653\/v1\/D15-1166"},{"key":"360_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, J., Du, J., Dai, L.: A gru-based encoder-decoder approach with attention for online handwritten mathematical expression recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 902\u2013907. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.152"},{"key":"360_CR23","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.patcog.2017.06.017","volume":"71","author":"J Zhang","year":"2017","unstructured":"Zhang, J., Du, J., Zhang, S., Liu, D., Hu, Y., Hu, J., Wei, S., Dai, L.: Watch, attend and parse: an end-to-end neural network based approach to handwritten mathematical expression recognition. Pattern Recogn. 71, 196\u2013206 (2017)","journal-title":"Pattern Recogn."},{"key":"360_CR24","unstructured":"Deng, Y., Kanervisto, A., Ling, J., Rush, A.M.: Image-to-markup generation with coarse-to-fine attention. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 980\u2013989 (2017)"},{"key":"360_CR25","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.procs.2019.01.246","volume":"147","author":"J Wang","year":"2019","unstructured":"Wang, J., Sun, Y., Wang, S.: Image to latex with DenseNet encoder and joint attention. Procedia Comput. Sci. 147, 374\u2013380 (2019)","journal-title":"Procedia Comput. Sci."},{"key":"360_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"360_CR27","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.-S.: Sca-cnn: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"360_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, W., Bai, Z., Zhu, Y.: An improved approach based on CNN-RNNs for mathematical expression recognition. In: Proceedings of the 2019 4th International Conference on Multimedia Systems and Signal Processing, pp. 57\u2013610. ACM (2019)","DOI":"10.1145\/3330393.3330410"},{"key":"360_CR29","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"360_CR30","unstructured":"Levy O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. In: Advances in Neural Information Processing Systems, pp. 2177\u20132185 (2014)"},{"issue":"8","key":"360_CR31","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"2","key":"360_CR32","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"key":"360_CR33","first-page":"129","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, p. 129. MIT Press, Cambridge (2016)"},{"key":"360_CR34","doi-asserted-by":"crossref","unstructured":"Shen, S., Cheng, Y., He, Z., He, W., Wu, H., Sun, M., Liu, Y.: Minimum risk training for neural machine translation (2015). arXiv preprint arXiv:1512.02433","DOI":"10.18653\/v1\/P16-1159"},{"key":"360_CR35","doi-asserted-by":"crossref","unstructured":"Wu, L., Tian, F., Qin, T., Lai, J., Liu, T.-Y.: A study of reinforcement learning for neural machine translation (2018). arXiv preprint arXiv:1808.08866","DOI":"10.18653\/v1\/D18-1397"},{"issue":"3\u20134","key":"360_CR36","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"360_CR37","unstructured":"Chatterjee S., Cancedda, N.: Minimum error rate training by sampling the translation lattice. In: Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pp. 606\u2013615. Association for Computational Linguistics (2010)"},{"key":"360_CR38","unstructured":"KaTex (2019, Aug 25). https:\/\/katex.org\/"},{"key":"360_CR39","doi-asserted-by":"crossref","unstructured":"\u00c1lvaro, F., S\u00e1nchez, J.-A., Bened\u00ed, J.-M.: An image-based measure for evaluation of mathematical expression recognition. In: Iberian Conference on Pattern Recognition and Image Analysis, pp. 682\u2013690. Springer (2013)","DOI":"10.1007\/978-3-642-38628-2_81"},{"key":"360_CR40","unstructured":"Mathpix Snip (2020, May 6th). https:\/\/mathpix.com\/"},{"key":"360_CR41","unstructured":"Kingma D.P., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"issue":"1","key":"360_CR42","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"360_CR43","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks (2012). arXiv preprint arXiv:1211.3711","DOI":"10.1007\/978-3-642-24797-2_3"},{"key":"360_CR44","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in pytorch (2017)"},{"key":"360_CR45","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014) arXiv preprint arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-020-00360-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-020-00360-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-020-00360-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,17]],"date-time":"2024-08-17T03:17:55Z","timestamp":1723864675000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-020-00360-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,8]]},"references-count":45,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["360"],"URL":"https:\/\/doi.org\/10.1007\/s10032-020-00360-2","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,8]]},"assertion":[{"value":"7 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}