{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T18:23:59Z","timestamp":1780597439643,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":46,"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\/3395027.3419585","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":9,"title":["Order out of Chaos"],"prefix":"10.1145","author":[{"given":"Isaac","family":"Alpizar-Chacon","sequence":"first","affiliation":[{"name":"Utrecht University, Utrecht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Sosnovsky","sequence":"additional","affiliation":[{"name":"Utrecht University, Utrecht, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The Chicago Manual of Style (17 ed.)","unstructured":"2017. The Chicago Manual of Style (17 ed.) . The University of Chicago Press . 2017. The Chicago Manual of Style (17 ed.). The University of Chicago Press."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342220.3343671"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the First Workshop on Intelligent Textbooks","volume":"2384","author":"Alpizar-Chacon Isaac","year":"2019","unstructured":"Isaac Alpizar-Chacon and Sergey Sosnovsky . 2019 . Interlingua: Linking textbooks across different languages . In Proceedings of the First Workshop on Intelligent Textbooks , Vol. 2384 . CEUR-WS, 104--117. Isaac Alpizar-Chacon and Sergey Sosnovsky. 2019. Interlingua: Linking textbooks across different languages. In Proceedings of the First Workshop on Intelligent Textbooks, Vol. 2384. CEUR-WS, 104--117."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Second Workshop on Intelligent Textbooks. CEUR-WS.","author":"Alpizar-Chacon Isaac","unstructured":"Isaac Alpizar-Chacon , Max van der Hart, Zef S. Wiersma, et al. 2020. Transformation of PDF Textbooks into Intelligent Educational Resources . In Proceedings of the Second Workshop on Intelligent Textbooks. CEUR-WS. Isaac Alpizar-Chacon, Max van der Hart, Zef S. Wiersma, et al. 2020. Transformation of PDF Textbooks into Intelligent Educational Resources. In Proceedings of the Second Workshop on Intelligent Textbooks. CEUR-WS."},{"key":"e_1_3_2_1_5_1","volume-title":"Intelligent Computer Mathematics","author":"Baker Josef B.","unstructured":"Josef B. Baker , Alan P. Sexton , and Volker Sorge . 2009. A Linear Grammar Approach to Mathematical Formula Recognition from PDF . In Intelligent Computer Mathematics . Springer Berlin Heidelberg , Berlin, Heidelberg , 201--216. Josef B. Baker, Alan P. Sexton, and Volker Sorge. 2009. A Linear Grammar Approach to Mathematical Formula Recognition from PDF. In Intelligent Computer Mathematics. Springer Berlin Heidelberg, Berlin, Heidelberg, 201--216."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2017.7991564"},{"key":"e_1_3_2_1_7_1","first-page":"993","article-title":"Latent dirichlet allocation","author":"Blei David M.","year":"2003","unstructured":"David M. Blei , Andrew Y. Ng , and Michael I. Jordan . 2003 . Latent dirichlet allocation . Journal of machine Learning research 3 , Jan (2003), 993 -- 1022 . David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022.","journal-title":"Journal of machine Learning research 3"},{"key":"e_1_3_2_1_8_1","volume-title":"The characteristics of well-designed science textbooks. The psychology of science text comprehension","author":"Chambliss Marilyn J.","year":"2002","unstructured":"Marilyn J. Chambliss . 2002. The characteristics of well-designed science textbooks. The psychology of science text comprehension ( 2002 ), 51--72. Marilyn J. Chambliss. 2002. The characteristics of well-designed science textbooks. The psychology of science text comprehension (2002), 51--72."},{"key":"e_1_3_2_1_9_1","volume-title":"Document Analysis Systems VI.","author":"Chao Hui","unstructured":"Hui Chao and Jian Fan . 2004. Layout and Content Extraction for PDF Documents . In Document Analysis Systems VI. Vol. 3163 . 213--224. Hui Chao and Jian Fan. 2004. Layout and Content Extraction for PDF Documents. In Document Analysis Systems VI. Vol. 3163. 213--224."},{"key":"e_1_3_2_1_10_1","volume-title":"International Language Resources and Evaluation","author":"Isaac G. Council","unstructured":"Isaac G. Council l, C. Lee Giles , and Min yen Kan . 2008. ParsCit: An open-source CRF reference string parsing package . In International Language Resources and Evaluation . European Language Resources Association . Isaac G. Councill, C. Lee Giles, and Min yen Kan. 2008. ParsCit: An open-source CRF reference string parsing package. In International Language Resources and Evaluation. European Language Resources Association."},{"key":"e_1_3_2_1_11_1","volume-title":"Berk","author":"Devore Jay L.","year":"2012","unstructured":"Jay L. Devore and Kenneth N . Berk . 2012 . Modern Mathematical Statistics with Applications. Springer . Jay L. Devore and Kenneth N. Berk. 2012. Modern Mathematical Statistics with Applications. Springer."},{"key":"e_1_3_2_1_12_1","volume-title":"ICDAR 2013 competition on book structure extraction. In 2013 12th International Conference on Document Analysis and Recognition. IEEE, 1438--1443","author":"Doucet Antoine","year":"2013","unstructured":"Antoine Doucet , Gabriella Kazai , Sebastian Colutto , 2013 . ICDAR 2013 competition on book structure extraction. In 2013 12th International Conference on Document Analysis and Recognition. IEEE, 1438--1443 . Antoine Doucet, Gabriella Kazai, Sebastian Colutto, et al. 2013. ICDAR 2013 competition on book structure extraction. In 2013 12th International Conference on Document Analysis and Recognition. IEEE, 1438--1443."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Antoine Doucet Gabriella Kazai Bodin Dresevic etal 2011. Setting up a competition framework for the evaluation of structure extraction from OCR-ed books. 14 (2011) 45--52.  Antoine Doucet Gabriella Kazai Bodin Dresevic et al. 2011. Setting up a competition framework for the evaluation of structure extraction from OCR-ed books. 14 (2011) 45--52.","DOI":"10.1007\/s10032-010-0127-3"},{"key":"e_1_3_2_1_14_1","volume-title":"Clara Mart\u00ednez Cant\u00f3n, et al.","author":"Fabo Pablo Ruiz","year":"2018","unstructured":"Pablo Ruiz Fabo , Helena Berm\u00fadez Sabel , Clara Mart\u00ednez Cant\u00f3n, et al. 2018 . The Diachronic Spanish Sonnet Corpus (DISCO): TEI and Linked Open Data Encoding, Data Distribution and Metrical Findings. In Digital Humanities 2018, Book of Abstracts . Pablo Ruiz Fabo, Helena Berm\u00fadez Sabel, Clara Mart\u00ednez Cant\u00f3n, et al. 2018. The Diachronic Spanish Sonnet Corpus (DISCO): TEI and Linked Open Data Encoding, Data Distribution and Metrical Findings. In Digital Humanities 2018, Book of Abstracts."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.304"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2008.30"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.143"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1998076.1998079"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40814-4_11"},{"key":"e_1_3_2_1_20_1","volume-title":"Expository text comprehension: Helping primary-grade teachers use expository texts to full advantage. Reading psychology 26, 3","author":"Hall Kendra M.","year":"2005","unstructured":"Kendra M. Hall , Brenda L. Sabey , and Michelle McClellan . 2005. Expository text comprehension: Helping primary-grade teachers use expository texts to full advantage. Reading psychology 26, 3 ( 2005 ), 211--234. Kendra M. Hall, Brenda L. Sabey, and Michelle McClellan. 2005. Expository text comprehension: Helping primary-grade teachers use expository texts to full advantage. Reading psychology 26, 3 (2005), 211--234."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1600193.1600206"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1045\/july2012-kern"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1045\/september2013-kern"},{"key":"e_1_3_2_1_25_1","first-page":"1","article-title":"Automatic Generation of the Domain Module from Electronic Textbooks","volume":"26","author":"Larra\u00f1aga Mikel","year":"2014","unstructured":"Mikel Larra\u00f1aga , Angel Conde , Inaki Calvo , 2014 . Automatic Generation of the Domain Module from Electronic Textbooks : Method and Validation. IEEE Trans. on Knowl. and Data Eng. 26 , 1 (Jan. 2014), 69--82. Mikel Larra\u00f1aga, Angel Conde, Inaki Calvo, et al. 2014. Automatic Generation of the Domain Module from Electronic Textbooks: Method and Validation. IEEE Trans. on Knowl. and Data Eng. 26, 1 (Jan. 2014), 69--82.","journal-title":"Method and Validation. IEEE Trans. on Knowl. and Data Eng."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30139-4_17"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.285"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.12"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 2012 ACM symposium on Document engineering. 37","author":"Ramanathan Chandrashekar","year":"2012","unstructured":"Chandrashekar Ramanathan , Yogalakshmi Jayabal , and Mehul Jayprakash Sheth . 2012 . Challenges in generating bookmarks from TOC entries in e-books . In Proceedings of the 2012 ACM symposium on Document engineering. 37 . Chandrashekar Ramanathan, Yogalakshmi Jayabal, and Mehul Jayprakash Sheth. 2012. Challenges in generating bookmarks from TOC entries in e-books. In Proceedings of the 2012 ACM symposium on Document engineering. 37."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"P. Ramnarayan A. Tomlinson A. Rao etal 2003. ISABEL: a web-based differential diagnostic aid for paediatrics: results from an initial performance evaluation. Archives of disease in childhood 88 5 (2003) 408--413.  P. Ramnarayan A. Tomlinson A. Rao et al. 2003. ISABEL: a web-based differential diagnostic aid for paediatrics: results from an initial performance evaluation. Archives of disease in childhood 88 5 (2003) 408--413.","DOI":"10.1136\/adc.88.5.408"},{"key":"e_1_3_2_1_31_1","volume-title":"Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5","author":"Salton Gerard","year":"1988","unstructured":"Gerard Salton and Christopher Buckley . 1988. Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5 ( 1988 ), 513--523. Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information processing & management 24, 5 (1988), 513--523."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"e_1_3_2_1_33_1","volume-title":"International Workshop on Graphics Recognition.","author":"Shao Mingyan","unstructured":"Mingyan Shao and Robert P. Futrelle . 2005. Recognition and classification of figures in PDF documents . In International Workshop on Graphics Recognition. Mingyan Shao and Robert P. Futrelle. 2005. Recognition and classification of figures in PDF documents. In International Workshop on Graphics Recognition."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33263-0_38"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities. 181--186","author":"Stahn Lena-Luise","year":"2016","unstructured":"Lena-Luise Stahn , Steffen Hennicke , and Ernesto William De Luca . 2016 . Using TEI for textbook research . In Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities. 181--186 . Lena-Luise Stahn, Steffen Hennicke, and Ernesto William De Luca. 2016. Using TEI for textbook research. In Proceedings of the Workshop on Language Technology Resources and Tools for Digital Humanities. 181--186."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation.","author":"Tittel Sabine","year":"2018","unstructured":"Sabine Tittel , Helena Berm\u00fadez-Sabel , and Christian Chiarcos . 2018 . Using RDFa to Link Text and Dictionary Data for Medieval French . In Proceedings of the Eleventh International Conference on Language Resources and Evaluation. Sabine Tittel, Helena Berm\u00fadez-Sabel, and Christian Chiarcos. 2018. Using RDFa to Link Text and Dictionary Data for Medieval French. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0249-8"},{"key":"e_1_3_2_1_38_1","volume-title":"Automatic Detection of Pseudocodes in Scholarly Documents Using Machine Learning. In 2013 12th International Conference on Document Analysis and Recognition.","author":"Tuarob Suppawong","year":"2013","unstructured":"Suppawong Tuarob , Sumit Bhatia , Prasenjit Mitra , 2013 . Automatic Detection of Pseudocodes in Scholarly Documents Using Machine Learning. In 2013 12th International Conference on Document Analysis and Recognition. Suppawong Tuarob, Sumit Bhatia, Prasenjit Mitra, et al. 2013. Automatic Detection of Pseudocodes in Scholarly Documents Using Machine Learning. In 2013 12th International Conference on Document Analysis and Recognition."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2016.2546302"},{"key":"e_1_3_2_1_40_1","volume-title":"2015 13th International Conference on Document Analysis and Recognition","author":"Tuarob Suppawong","year":"2015","unstructured":"Suppawong Tuarob , Prasenjit Mitra , and C. Lee Giles . 2015. A hybrid approach to discover semantic hierarchical sections in scholarly documents . 2015 13th International Conference on Document Analysis and Recognition ( 2015 ), 1081--1085. Suppawong Tuarob, Prasenjit Mitra, and C. Lee Giles. 2015. A hybrid approach to discover semantic hierarchical sections in scholarly documents. 2015 13th International Conference on Document Analysis and Recognition (2015), 1081--1085."},{"key":"e_1_3_2_1_41_1","unstructured":"Ronald E. Walpole Raymond H. Myers Sharon L. Myers etal 2012. Probability & statistics for engineers & scientists. Prentice Hall.  Ronald E. Walpole Raymond H. Myers Sharon L. Myers et al. 2012. Probability & statistics for engineers & scientists. Prentice Hall."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2682571.2797062"},{"key":"e_1_3_2_1_43_1","unstructured":"John Whitington. 2011. PDF Explained. O'Reilly Media Chapter I Introduction.  John Whitington. 2011. PDF Explained. O'Reilly Media Chapter I Introduction."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v36i3.2601"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2494266.2494282"},{"key":"e_1_3_2_1_46_1","volume-title":"2013 12th International Conference on Document Analysis and Recognition. 1205--1209","author":"Wu Zhaohui","unstructured":"Zhaohui Wu , Prasenjit Mitra , and C. Lee Giles . 2013. Table of contents recognition and extraction for heterogeneous book documents . In 2013 12th International Conference on Document Analysis and Recognition. 1205--1209 . Zhaohui Wu, Prasenjit Mitra, and C. Lee Giles. 2013. Table of contents recognition and extraction for heterogeneous book documents. In 2013 12th International Conference on Document Analysis and Recognition. 1205--1209."}],"event":{"name":"DocEng '20: ACM Symposium on Document Engineering 2020","location":"Virtual Event CA USA","acronym":"DocEng '20","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGDOC ACM Special Interest Group for Design of Communications"]},"container-title":["Proceedings of the ACM Symposium on Document Engineering 2020"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395027.3419585","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3395027.3419585","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\/3395027.3419585"}},"subtitle":["Construction of Knowledge Models from PDF Textbooks"],"short-title":[],"issued":{"date-parts":[[2020,9,29]]},"references-count":46,"alternative-id":["10.1145\/3395027.3419585","10.1145\/3395027"],"URL":"https:\/\/doi.org\/10.1145\/3395027.3419585","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"}}]}}