{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:53:00Z","timestamp":1757544780355},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642405006"},{"type":"electronic","value":"9783642405013"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-40501-3_15","type":"book-chapter","created":{"date-parts":[[2013,8,30]],"date-time":"2013-08-30T04:37:43Z","timestamp":1377837463000},"page":"144-155","source":"Crossref","is-referenced-by-count":15,"title":["An Unsupervised Machine Learning Approach to Body Text and Table of Contents Extraction from Digital Scientific Articles"],"prefix":"10.1007","author":[{"given":"Stefan","family":"Klampfl","sequence":"first","affiliation":[]},{"given":"Roman","family":"Kern","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1117\/12.476326","volume":"5010","author":"S. Mao","year":"2003","unstructured":"Mao, S., Rosenfeld, A., Kanungo, T.: Document structure analysis algorithms: A literature survey. Proceedings of SPIE\u00a05010(1), 197\u2013207 (2003)","journal-title":"Proceedings of SPIE"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Kern, R., Jack, K., Hristakeva, M., Granitzer, M.: TeamBeam - Meta-Data Extraction from Scientific Literature. In: 1st International Workshop on Mining Scientific Publications (2012)","DOI":"10.1045\/july2012-kern"},{"key":"15_CR3","unstructured":"Peng, F., McCallum, A.: Accurate Information Extraction from Research Papers using Conditional Random Fields. In: HLTNAACL 2004, vol.\u00a02004, pp. 329\u2013336 (2004)"},{"key":"15_CR4","unstructured":"Councill, I.G., Giles, C.L., Kan, M.Y.: ParsCit: An open-source CRF Reference String Parsing Package. In: Proceedings of LREC, vol. 2008, pp. 661\u2013667. Citeseer, European Language Resources Association, ELRA (2008)"},{"issue":"4","key":"15_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdls.2010100101","volume":"1","author":"M.T. Luong","year":"2011","unstructured":"Luong, M.T., Nguyen, T.D., Kan, M.Y.: Logical structure recovery in scholarly articles with rich document features. International Journal of Digital Library Systems\u00a01(4), 1\u201323 (2011)","journal-title":"International Journal of Digital Library Systems"},{"issue":"1","key":"15_CR6","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/1751-0473-7-7","volume":"7","author":"C. Ramakrishnan","year":"2012","unstructured":"Ramakrishnan, C., Patnia, A., Hovy, E., Burns, G.A.: Layout-Aware Text Extraction from Full-text PDF of Scientific Articles. Source Code for Biology and Medicine\u00a07(1), 7 (2012)","journal-title":"Source Code for Biology and Medicine"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Gao, L., Tang, Z., Lin, X., Liu, Y., Qiu, R., Wang, Y.: Structure extraction from PDF-based book documents. In: Proceedings of the 11th Annual International ACM\/IEEE Joint Conference on Digital Libraries, pp. 11\u201320 (2011)","DOI":"10.1145\/1998076.1998079"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1117\/12.472833","volume":"5010","author":"X. Lin","year":"2002","unstructured":"Lin, X.: Header and Footer Extraction by Page-Association. Proceedings of SPIE\u00a05010, 164\u2013171 (2002)","journal-title":"Proceedings of SPIE"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Granitzer, M., Hristakeva, M., Knight, R., Jack, K., Kern, R.: A Comparison of Layout based Bibliographic Metadata Extraction Techniques. In: WIMS 2012 - International Conference on Web Intelligence, Mining and Semantics, pp. 19:1\u201319:8. ACM, New York (2012)","DOI":"10.1145\/2254129.2254154"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Y., Mitra, P., Giles, C.L.: Identifying table boundaries in digital documents via sparse line detection. In: Proceeding of the 17th ACM Conference on Information and Knowledge Mining, CIKM 2008, pp. 1311\u20131320. ACM Press (2008)","DOI":"10.1145\/1458082.1458255"},{"issue":"1","key":"15_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10032-002-0080-x","volume":"5","author":"M. Aiello","year":"2002","unstructured":"Aiello, M., Monz, C., Todoran, L., Worring, M.: Document understanding for a broad class of documents. International Journal on Document Analysis and Recognition\u00a05(1), 1\u201316 (2002)","journal-title":"International Journal on Document Analysis and Recognition"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Malerba, D., Ceci, M., Berardi, M.: Machine learning for reading order detection in document image understanding. Machine Learning in Document Analysis, 45\u201369 (2008)","DOI":"10.1007\/978-3-540-76280-5_3"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Tkaczyk, D., Czeczko, A., Rusek, K.: GROTOAP: ground truth for open access publications. In: Proceedings of the 12th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 381\u2013382 (2012)","DOI":"10.1145\/2232817.2232901"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Tkaczyk, D., Bolikowski, L., Czeczko, A., Rusek, K.: A Modular Metadata Extraction System for Born-Digital Articles. In: 2012 10th IAPR International Workshop on Document Analysis Systems, pp. 11\u201316 (March 2012)","DOI":"10.1109\/DAS.2012.4"},{"issue":"6","key":"15_CR15","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"K. Zhang","year":"1989","unstructured":"Zhang, K., Shasha, D.: Simple Fast Algorithms for the Editing Distance between Trees and Related Problems. SIAM Journal on Computing\u00a018(6), 1245\u20131262 (1989)","journal-title":"SIAM Journal on Computing"}],"container-title":["Lecture Notes in Computer Science","Research and Advanced Technology for Digital Libraries"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-40501-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T00:45:15Z","timestamp":1558053915000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-40501-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642405006","9783642405013"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-40501-3_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}