{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:53Z","timestamp":1763468273957,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,10,7]],"date-time":"2015-10-07T00:00:00Z","timestamp":1444176000000},"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":[[2015,10,7]]},"DOI":"10.1145\/2815833.2815834","type":"proceedings-article","created":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T19:22:30Z","timestamp":1443554550000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["PDFMEF"],"prefix":"10.1145","author":[{"given":"Jian","family":"Wu","sequence":"first","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Killian","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaiyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Williams","sequence":"additional","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sagnik Ray","family":"Choudhury","sequence":"additional","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suppawong","family":"Tuarob","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelia","family":"Caragea","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of North Texas, Denton, TX, 76203 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. Lee","family":"Giles","sequence":"additional","affiliation":[{"name":"Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802 USA and Computer Science and Engineering, Pennsylvania State University, University Park, PA, 16802 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,10,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Pdflib tet. http:\/\/www.pdflib.com\/products\/tet\/. Accessed: 2015-05-12.  Pdflib tet. http:\/\/www.pdflib.com\/products\/tet\/. Accessed: 2015-05-12."},{"key":"e_1_3_2_1_2_1","unstructured":"Poppler. http:\/\/poppler.freedesktop.org. Accessed: 2015-05-12.  Poppler. http:\/\/poppler.freedesktop.org. Accessed: 2015-05-12."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Tabula. http:\/\/tabula.technology. Accessed: 2015-05-13.  Tabula. http:\/\/tabula.technology. Accessed: 2015-05-13.","DOI":"10.32728\/tab.13.1.2015.01"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1985429.1985433"},{"key":"e_1_3_2_1_5_1","volume-title":"WSDM 2014 Workshop on Web-scale Classification: Classifying Big Data from the Web","author":"Caragea C.","year":"2014","unstructured":"C. Caragea , J. Wu , K. Williams , S. D. Gollapalli , M. Khabsa , and C. L. Giles . Automatic identification of research articles from crawled documents . WSDM 2014 Workshop on Web-scale Classification: Classifying Big Data from the Web , 2014 . C. Caragea, J. Wu, K. Williams, S. D. Gollapalli, M. Khabsa, and C. L. Giles. Automatic identification of research articles from crawled documents. WSDM 2014 Workshop on Web-scale Classification: Classifying Big Data from the Web, 2014."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1298406.1298435"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.34"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2467696.2467757"},{"key":"e_1_3_2_1_9_1","volume-title":"AAAI 2015 Workshop on Scholarly Big Data","author":"Clark C.","year":"2015","unstructured":"C. Clark and S. Divvala . Looking beyond text: Extracting figures, tables, and captions from computer science paper . AAAI 2015 Workshop on Scholarly Big Data , 2015 . C. Clark and S. Divvala. Looking beyond text: Extracting figures, tables, and captions from computer science paper. AAAI 2015 Workshop on Scholarly Big Data, 2015."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597763"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2391200.2391214"},{"key":"e_1_3_2_1_12_1","volume-title":"TEI P5: Guidelines for Electronic Text Encoding and Interchange 2.3.0","author":"T. Consortium","year":"2013","unstructured":"T. Consortium . TEI P5: Guidelines for Electronic Text Encoding and Interchange 2.3.0 . TEI Consortium , 2013 . T. Consortium. TEI P5: Guidelines for Electronic Text Encoding and Interchange 2.3.0. TEI Consortium, 2013."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08)","author":"I. Council","year":"2008","unstructured":"I. Council l, C. L. Giles , and M.-Y. Kan . Parscit : an open-source crf reference string parsing package . In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08) , Marrakech, Morocco, may 2008 . European Language Resources Association (ELRA). I. Councill, C. L. Giles, and M.-Y. Kan. Parscit: an open-source crf reference string parsing package. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco, may 2008. European Language Resources Association (ELRA)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088622.1088627"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/476025a"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324904003523"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775250"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/827140.827146"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0093949"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-010-0202-z"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2467696.2467753"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1141753.1141835"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2011.26"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/1812799.1812875"},{"key":"e_1_3_2_1_25_1","volume-title":"AAAI'99 Workshop on Machine Learning for Information Extraction","author":"Seymore K.","year":"1999","unstructured":"K. Seymore , A. McCallum , and R. Rosenfeld . Learning hidden markov model structure for information extraction . AAAI'99 Workshop on Machine Learning for Information Extraction , 1999 . K. Seymore, A. McCallum, and R. Rosenfeld. Learning hidden markov model structure for information extraction. AAAI'99 Workshop on Machine Learning for Information Extraction, 1999."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961209.1961215"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.151"},{"key":"e_1_3_2_1_28_1","volume-title":"Proeedings of the tenth International Python Conference","author":"Wang L.","year":"2002","unstructured":"L. Wang and P. Pfeiffer . A qualitative analysis of the usability of perl, python, and tcl . In Proeedings of the tenth International Python Conference , 2002 . L. Wang and P. Pfeiffer. A qualitative analysis of the usability of perl, python, and tcl. In Proeedings of the tenth International Python Conference, 2002."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/2892753.2892957"}],"event":{"name":"K-CAP 2015: Knowledge Capture Conference","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"location":"Palisades NY USA","acronym":"K-CAP 2015"},"container-title":["Proceedings of the 8th International Conference on Knowledge Capture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2815833.2815834","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2815833.2815834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:48:23Z","timestamp":1750225703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2815833.2815834"}},"subtitle":["A Multi-Entity Knowledge Extraction Framework for Scholarly Documents and Semantic Search"],"short-title":[],"issued":{"date-parts":[[2015,10,7]]},"references-count":29,"alternative-id":["10.1145\/2815833.2815834","10.1145\/2815833"],"URL":"https:\/\/doi.org\/10.1145\/2815833.2815834","relation":{},"subject":[],"published":{"date-parts":[[2015,10,7]]},"assertion":[{"value":"2015-10-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}