{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:06:40Z","timestamp":1743026800453,"version":"3.40.3"},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319465647"},{"type":"electronic","value":"9783319465654"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46565-4_23","type":"book-chapter","created":{"date-parts":[[2016,10,8]],"date-time":"2016-10-08T07:20:30Z","timestamp":1475911230000},"page":"293-308","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Information Extraction from PDF Sources Based on Rule-Based System Using Integrated Formats"],"prefix":"10.1007","author":[{"given":"Riaz","family":"Ahmad","sequence":"first","affiliation":[]},{"given":"Muhammad Tanvir","family":"Afzal","sequence":"additional","affiliation":[]},{"given":"Muhammad Abdul","family":"Qadir","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,9]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Do, H.H.N., Chandrasekaran, M.K., Cho, P.S., Kan, M.Y.: Extracting and matching authors and affiliations in scholarly documents. In: Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 219\u2013228. ACM (2013)","DOI":"10.1145\/2467696.2467703"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Di Iorio, A., Peroni, S., Poggi, F., Vitali, F., Shotton, D.: Recognising document components in XML-based academic articles. In: Proceedings of the 2013 ACM Symposium on Document Engineering, pp. 181\u2013184. ACM (2013)","DOI":"10.1145\/2494266.2494319"},{"key":"23_CR3","unstructured":"Kim, S., Cho, Y., Ahn, K.: Semi-automatic metadata extraction from scientific journal article for full-text XML conversion. In: Proceedings of the International Conference on Data Mining (DMIN), p. 1 (2014). The Steering Committee of the World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp)"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Nguyen, T.D., Kan, M.Y.: Logical structure recovery in scholarly articles with rich document features. In: Multimedia Storage and Retrieval Innovations for Digital Library Systems, vol. 270 (2012)","DOI":"10.4018\/978-1-4666-0900-6.ch014"},{"key":"23_CR5","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-319-25518-7_7","volume-title":"Semantic Web Evaluation Challenges","author":"M Milicka","year":"2015","unstructured":"Milicka, M., Burget, R.: Information extraction from web sources based on multi-aspect content analysis. In: Gandon, F., et al. (eds.) SemWebEval 2015. CCIS, vol. 548, pp. 81\u201392. Springer, Heidelberg (2015). doi:\n                    10.1007\/978-3-319-25518-7_7"},{"issue":"2","key":"23_CR6","first-page":"81","volume":"1","author":"R Mohemad","year":"2011","unstructured":"Mohemad, R., Hamdan, A.R., Othman, Z.A., Noor, N.M.: Automatic document structure analysis of structured PDF files. Int. J. New Comput. Architect. Appl. (IJNCAA) 1(2), 404\u2013411 (2011)","journal-title":"Int. J. New Comput. Architect. Appl. (IJNCAA)"},{"issue":"12","key":"23_CR7","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.14778\/2824032.2824058","volume":"8","author":"T Manabe","year":"2015","unstructured":"Manabe, T., Tajima, K.: Extracting logical hierarchical structure of HTML documents based on headings. Proc. VLDB Endow. 8(12), 1606\u20131617 (2015)","journal-title":"Proc. VLDB Endow."},{"key":"23_CR8","unstructured":"Nuno, M., F\u00e1tima, R.: Extracting structure, text and entities from PDF documents of the portuguese legislation. Institute of Engineering, Polytechnic of Porto, Portugal (2012)"},{"issue":"1","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1","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 Biol. Med. 7(1), 1 (2012)","journal-title":"Source Code Biol. Med."},{"key":"23_CR10","unstructured":"Saleem, O., Latif, S.: Information extraction from research papers by data integration and data validation from multiple header extraction sources. In: Proceedings of the World Congress on Engineering and Computer Science, vol. 1 (2012)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Constantin, A., Pettifer, S., Voronkov, A.: PDFX: fully-automated PDF-to-XML conversion of scientific literature. In: Proceedings of the 2013 ACM Symposium on Document Engineering, pp. 177\u2013180. ACM (2013)","DOI":"10.1145\/2494266.2494271"}],"container-title":["Communications in Computer and Information Science","Semantic Web Challenges"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46565-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T23:25:24Z","timestamp":1558394724000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46565-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319465647","9783319465654"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46565-4_23","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"9 October 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SemWebEval","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Semantic Web Evaluation Challenge","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 June 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"semwebeval2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}