{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:04:28Z","timestamp":1767773068202,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,29]],"date-time":"2020-09-29T00:00:00Z","timestamp":1601337600000},"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":[[2020,9,29]]},"DOI":"10.1145\/3395027.3419580","type":"proceedings-article","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T16:16:05Z","timestamp":1600877765000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["PDF2LaTeX"],"prefix":"10.1145","author":[{"given":"Zelun","family":"Wang","sequence":"first","affiliation":[{"name":"Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyh-Charn","family":"Liu","sequence":"additional","affiliation":[{"name":"Dept. of Computer Science and Engineering, Texas A&M University, College Station, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1087\/20100308"},{"key":"e_1_3_2_1_2_1","unstructured":"(2019 Feb 20). arXiv submission rate statistics. Available: https:\/\/arxiv.org\/help\/stats\/2019_by_area  (2019 Feb 20). arXiv submission rate statistics. Available: https:\/\/arxiv.org\/help\/stats\/2019_by_area"},{"key":"e_1_3_2_1_3_1","unstructured":"(2019 Feb 7th). PDFMiner. Available: https:\/\/pypi.org\/project\/pdfminer\/  (2019 Feb 7th). PDFMiner. Available: https:\/\/pypi.org\/project\/pdfminer\/"},{"key":"e_1_3_2_1_4_1","unstructured":"\"Document management - Portable document format - Part 1: PDF 1.7 \" Adobe Systems Incorporated p. 242 July 1st 2008.  \"Document management - Portable document format - Part 1: PDF 1.7 \" Adobe Systems Incorporated p. 242 July 1st 2008."},{"volume-title":"Sydney","author":"Wang Z.","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-011-0174-4"},{"key":"e_1_3_2_1_7_1","unstructured":"(2020 Feb 20th). NIST Digital Library of Mathematical Functions. Available: https:\/\/dlmf.nist.gov\/  (2020 Feb 20th). NIST Digital Library of Mathematical Functions. Available: https:\/\/dlmf.nist.gov\/"},{"key":"e_1_3_2_1_8_1","unstructured":"(2020 Feb 20th). Wolfram Functions Site. Available: http:\/\/functions.wolfram.com\/  (2020 Feb 20th). Wolfram Functions Site. Available: http:\/\/functions.wolfram.com\/"},{"key":"e_1_3_2_1_9_1","unstructured":"P. Ion R. Miner S. Buswell and A. Devitt Mathematical Markup Language (MathML) 1.0 Specification. World Wide Web Consortium (W3C) 1998.  P. Ion R. Miner S. Buswell and A. Devitt Mathematical Markup Language (MathML) 1.0 Specification. World Wide Web Consortium (W3C) 1998."},{"key":"e_1_3_2_1_10_1","unstructured":"E. Foulke \"Reading braille \" Tactual perception: A sourcebook vol. 168 1982.  E. Foulke \"Reading braille \" Tactual perception: A sourcebook vol. 168 1982."},{"key":"e_1_3_2_1_11_1","unstructured":"(2020 Feb 7th). Apache PDFBox. Available: https:\/\/pdfbox.apache.org\/  (2020 Feb 7th). Apache PDFBox. Available: https:\/\/pdfbox.apache.org\/"},{"issue":"6","key":"e_1_3_2_1_12_1","first-page":"545","article-title":"Optical character recognition techniques: a survey","volume":"4","author":"Singh S.","year":"2013","journal-title":"Journal of emerging Trends in Computing and information Sciences"},{"key":"e_1_3_2_1_13_1","unstructured":"K. Ashida M. Okamoto H. Imai and T. Nakatsuka \"Performance evaluation of a mathematical formula recognition system with a large scale of printed formula images \" in Second International Conference on Document Image Analysis for Libraries (DIAL'06) 2006 pp. 12 pp. 331: IEEE.  K. Ashida M. Okamoto H. Imai and T. Nakatsuka \"Performance evaluation of a mathematical formula recognition system with a large scale of printed formula images \" in Second International Conference on Document Image Analysis for Libraries (DIAL'06) 2006 pp. 12 pp. 331: IEEE."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"M. Suzuki F. Tamari R. Fukuda S. Uchida and T. Kanahori \"INFTY: an integrated OCR system for mathematical documents \" in Proceedings of the 2003 ACM symposium on Document engineering 2003 pp. 95--104: ACM.  M. Suzuki F. Tamari R. Fukuda S. Uchida and T. Kanahori \"INFTY: an integrated OCR system for mathematical documents \" in Proceedings of the 2003 ACM symposium on Document engineering 2003 pp. 95--104: ACM.","DOI":"10.1145\/958220.958239"},{"key":"e_1_3_2_1_15_1","unstructured":"Y. Deng A. Kanervisto J. Ling and A. M. Rush \"Image-to-markup generation with coarse-to-fine attention \" in Proceedings of the 34th International Conference on Machine Learning-Volume 70 2017 pp. 980--989: JMLR. org.  Y. Deng A. Kanervisto J. Ling and A. M. Rush \"Image-to-markup generation with coarse-to-fine attention \" in Proceedings of the 34th International Conference on Machine Learning-Volume 70 2017 pp. 980--989: JMLR. org."},{"key":"e_1_3_2_1_16_1","unstructured":"Z. Wang and J.-C. Liu \"Translating Mathematical Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training \" arXiv preprint arXiv: 1908.11415 2019.  Z. Wang and J.-C. Liu \"Translating Mathematical Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training \" arXiv preprint arXiv: 1908.11415 2019."},{"key":"e_1_3_2_1_17_1","first-page":"759","volume-title":"14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","volume":"1","author":"Wang X.","year":"2017"},{"volume-title":"IAPR International Conference on Document Analysis and Recognition (ICDAR)","year":"2019","author":"Wang X.","key":"e_1_3_2_1_18_1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"K. Iwatsuki T. Sagara T. Hara and A. Aizawa \"Detecting In-line Mathematical Expressions in Scientific Documents \" in Proceedings of the 2017 ACM Symposium on Document Engineering 2017 pp. 141--144: ACM.  K. Iwatsuki T. Sagara T. Hara and A. Aizawa \"Detecting In-line Mathematical Expressions in Scientific Documents \" in Proceedings of the 2017 ACM Symposium on Document Engineering 2017 pp. 141--144: ACM.","DOI":"10.1145\/3103010.3121041"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02614-0_19"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"J. B. Baker A. P. Sexton and V. Sorge \"Faithful mathematical formula recognition from PDF documents \" in Proceedings of the 9th IAPR International Workshop on Document Analysis Systems 2010 pp. 485--492: ACM.  J. B. Baker A. P. Sexton and V. Sorge \"Faithful mathematical formula recognition from PDF documents \" in Proceedings of the 9th IAPR International Workshop on Document Analysis Systems 2010 pp. 485--492: ACM.","DOI":"10.1145\/1815330.1815393"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"L. Gao X. Yi Y. Liao Z. Jiang Z. Yan and Z. Tang \"A Deep Learning-Based Formula Detection Method for PDF Documents \" in 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) 2017 pp. 553--558: IEEE.  L. Gao X. Yi Y. Liao Z. Jiang Z. Yan and Z. Tang \"A Deep Learning-Based Formula Detection Method for PDF Documents \" in 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) 2017 pp. 553--558: IEEE.","DOI":"10.1109\/ICDAR.2017.96"},{"key":"e_1_3_2_1_23_1","unstructured":"Y. Deng A. Kanervisto and A. M. Rush \"What you get is what you see: A visual markup decompiler \" arXiv preprint arXiv:1609.04938 vol. 10 pp. 32--37 2016.  Y. Deng A. Kanervisto and A. M. Rush \"What you get is what you see: A visual markup decompiler \" arXiv preprint arXiv:1609.04938 vol. 10 pp. 32--37 2016."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"R. Smith \"An overview of the Tesseract OCR engine \" in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) 2007 vol. 2 pp. 629--633: IEEE.  R. Smith \"An overview of the Tesseract OCR engine \" in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) 2007 vol. 2 pp. 629--633: IEEE.","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"e_1_3_2_1_25_1","unstructured":"M. O. Perez-Arriaga T. Estrada and S. Abad-Mota \"TAO: system for table detection and extraction from PDF documents \" in The Twenty-Ninth International Flairs Conference 2016.  M. O. Perez-Arriaga T. Estrada and S. Abad-Mota \"TAO: system for table detection and extraction from PDF documents \" in The Twenty-Ninth International Flairs Conference 2016."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"S. Schreiber S. Agne I. Wolf A. Dengel and S. Ahmed \"Deepdesrt: Deep learning for detection and structure recognition of tables in document images \" in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) 2017 vol. 1 pp. 1162--1167: IEEE.  S. Schreiber S. Agne I. Wolf A. Dengel and S. Ahmed \"Deepdesrt: Deep learning for detection and structure recognition of tables in document images \" in 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) 2017 vol. 1 pp. 1162--1167: IEEE.","DOI":"10.1109\/ICDAR.2017.192"},{"key":"e_1_3_2_1_27_1","unstructured":"C. Clark and S. Divvala \"Looking beyond text: Extracting figures tables and captions from computer science papers.. 2015 \" in AAAI 2015 Workshop on Scholarly Big Data 2015.  C. Clark and S. Divvala \"Looking beyond text: Extracting figures tables and captions from computer science papers.. 2015 \" in AAAI 2015 Workshop on Scholarly Big Data 2015."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"R. Saha A. Mondal and C. Jawahar \"Graphical Object Detection in Document Images \" in 2019 International Conference on Document Analysis and Recognition (ICDAR) 2019 pp. 51--58: IEEE.  R. Saha A. Mondal and C. Jawahar \"Graphical Object Detection in Document Images \" in 2019 International Conference on Document Analysis and Recognition (ICDAR) 2019 pp. 51--58: IEEE.","DOI":"10.1109\/ICDAR.2019.00018"},{"key":"e_1_3_2_1_29_1","unstructured":"A. Krizhevsky I. Sutskever and G. E. Hinton \"Imagenet classification with deep convolutional neural networks \" in Advances in neural information processing systems 2012 pp. 1097--1105.  A. Krizhevsky I. Sutskever and G. E. Hinton \"Imagenet classification with deep convolutional neural networks \" in Advances in neural information processing systems 2012 pp. 1097--1105."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/980972.980992"},{"key":"e_1_3_2_1_31_1","unstructured":"B. Miller \"LaTeXML: A Latex to XML Converter. url: https:\/\/dlmf.nist.gov\/LaTeXML\/ \" LaTeXML\/(visited on 03\/03\/2020).  B. Miller \"LaTeXML: A Latex to XML Converter. url: https:\/\/dlmf.nist.gov\/LaTeXML\/ \" LaTeXML\/(visited on 03\/03\/2020)."},{"key":"e_1_3_2_1_32_1","unstructured":"(2020 March 3). TeX Live. Available: https:\/\/www.tug.org\/texlive\/  (2020 March 3). TeX Live. Available: https:\/\/www.tug.org\/texlive\/"},{"key":"e_1_3_2_1_33_1","unstructured":"M. Lin Q. Chen and S. Yan \"Network in network \" arXiv preprint arXiv:1312.4400 2013.  M. Lin Q. Chen and S. Yan \"Network in network \" arXiv preprint arXiv:1312.4400 2013."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"B. Shi X. Bai and C. Yao \"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition \" IEEE transactions on pattern analysis and machine intelligence vol. 39 no. 11 pp. 2298--2304 2016.  B. Shi X. Bai and C. Yao \"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition \" IEEE transactions on pattern analysis and machine intelligence vol. 39 no. 11 pp. 2298--2304 2016.","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"e_1_3_2_1_35_1","unstructured":"A. Paszke et al. \"Automatic differentiation in pytorch \" 2017.  A. Paszke et al. \"Automatic differentiation in pytorch \" 2017."},{"key":"e_1_3_2_1_36_1","unstructured":"D. P. Kingma and J. Ba \"Adam: A method for stochastic optimization \" arXiv preprint arXiv:1412.6980 2014.  D. P. Kingma and J. Ba \"Adam: A method for stochastic optimization \" arXiv preprint arXiv:1412.6980 2014."},{"key":"e_1_3_2_1_37_1","unstructured":"N. Srivastava G. Hinton A. Krizhevsky I. Sutskever and R. Salakhutdinov \"Dropout: a simple way to prevent neural networks from overfitting \" The journal of machine learning research vol. 15 no. 1 pp. 1929--1958 2014.  N. Srivastava G. Hinton A. Krizhevsky I. Sutskever and R. Salakhutdinov \"Dropout: a simple way to prevent neural networks from overfitting \" The journal of machine learning research vol. 15 no. 1 pp. 1929--1958 2014."},{"key":"e_1_3_2_1_38_1","unstructured":"M. Korobov \"sklearn-crfsuite (2015) \" ed 2019.  M. Korobov \"sklearn-crfsuite (2015) \" ed 2019."},{"key":"e_1_3_2_1_39_1","unstructured":"A. Vaswani et al. \"Attention is all you need \" in Advances in neural information processing systems 2017 pp. 5998--6008.  A. Vaswani et al. \"Attention is all you need \" in Advances in neural information processing systems 2017 pp. 5998--6008."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"M.-T. Luong H. Pham and C. D. Manning \"Effective approaches to attention-based neural machine translation \" arXiv preprint arXiv:1508.04025 2015.  M.-T. Luong H. Pham and C. D. Manning \"Effective approaches to attention-based neural machine translation \" arXiv preprint arXiv:1508.04025 2015.","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_1_42_1","unstructured":"R. S. Sutton D. A. McAllester S. P. Singh and Y. Mansour \"Policy gradient methods for reinforcement learning with function approximation \" in Advances in neural information processing systems 2000 pp. 1057--1063.  R. S. Sutton D. A. McAllester S. P. Singh and Y. Mansour \"Policy gradient methods for reinforcement learning with function approximation \" in Advances in neural information processing systems 2000 pp. 1057--1063."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"K. Papineni S. Roukos T. Ward and W.-J. Zhu \"BLEU: a method for automatic evaluation of machine translation \" in Proceedings of the 40th annual meeting on association for computational linguistics 2002 pp. 311--318: Association for Computational Linguistics.  K. Papineni S. Roukos T. Ward and W.-J. Zhu \"BLEU: a method for automatic evaluation of machine translation \" in Proceedings of the 40th annual meeting on association for computational linguistics 2002 pp. 311--318: Association for Computational Linguistics.","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"A. Graves \"Sequence transduction with recurrent neural networks \" arXiv preprint arXiv:1211.3711 2012.  A. Graves \"Sequence transduction with recurrent neural networks \" arXiv preprint arXiv:1211.3711 2012.","DOI":"10.1007\/978-3-642-24797-2"},{"key":"e_1_3_2_1_45_1","unstructured":"(2019 Aug 25). KaTex. Available: https:\/\/katex.org\/  (2019 Aug 25). KaTex. Available: https:\/\/katex.org\/"}],"event":{"name":"DocEng '20: ACM Symposium on Document Engineering 2020","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGDOC ACM Special Interest Group for Design of Communications"],"location":"Virtual Event CA USA","acronym":"DocEng '20"},"container-title":["Proceedings of the ACM Symposium on Document Engineering 2020"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395027.3419580","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3395027.3419580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:01Z","timestamp":1750193281000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395027.3419580"}},"subtitle":["A Deep Learning System to Convert Mathematical Documents from PDF to LaTeX"],"short-title":[],"issued":{"date-parts":[[2020,9,29]]},"references-count":45,"alternative-id":["10.1145\/3395027.3419580","10.1145\/3395027"],"URL":"https:\/\/doi.org\/10.1145\/3395027.3419580","relation":{},"subject":[],"published":{"date-parts":[[2020,9,29]]},"assertion":[{"value":"2020-09-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}