{"id":"https://openalex.org/W3094362450","doi":"https://doi.org/10.5220/0010131402350242","title":"Extracting Body Text from Academic PDF Documents for Text Mining","display_name":"Extracting Body Text from Academic PDF Documents for Text Mining","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3094362450","doi":"https://doi.org/10.5220/0010131402350242","mag":"3094362450"},"language":"en","primary_location":{"id":"doi:10.5220/0010131402350242","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010131402350242","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010131402350242","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109920381","display_name":"Chang\u2010Feng Yu","orcid":"https://orcid.org/0000-0003-3298-8941"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changfeng Yu","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439655","display_name":"Cheng Zhang","orcid":"https://orcid.org/0000-0002-7196-9463"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Zhang","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100731879","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0001-6423-826X"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Lowell, MA, U.S.A., --- Select a Country ---","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.836286187171936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106116056442261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5982683897018433},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5684689283370972},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5585017204284668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521379292011261},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5162639617919922},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.46908488869667053},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17334625124931335},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10792046785354614}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.836286187171936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106116056442261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5982683897018433},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5684689283370972},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5585017204284668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521379292011261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5162639617919922},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.46908488869667053},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17334625124931335},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10792046785354614}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0010131402350242","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010131402350242","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0010131402350242","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010131402350242","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1506666816","https://openalex.org/W1996430422","https://openalex.org/W2064354603","https://openalex.org/W2399857077","https://openalex.org/W2518276024","https://openalex.org/W2577020101","https://openalex.org/W2740245131","https://openalex.org/W2742875101","https://openalex.org/W2890767379","https://openalex.org/W2963563735","https://openalex.org/W2989445916","https://openalex.org/W3012516156","https://openalex.org/W3023097746","https://openalex.org/W3032127765"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W4200355488","https://openalex.org/W2391800119","https://openalex.org/W2595239241","https://openalex.org/W2799181378","https://openalex.org/W2052919063","https://openalex.org/W3003711649","https://openalex.org/W2904173691","https://openalex.org/W4365517254","https://openalex.org/W270947280"],"abstract_inverted_index":{"Accurate":[0],"extraction":[1],"of":[2,129],"body":[3,27,52],"text":[4,28,45,74,77,89,120],"from":[5,46,134],"PDF-formatted":[6],"academic":[7,138],"documents":[8,48,131],"is":[9,20,99],"essential":[10],"in":[11,25,82],"text-mining":[12],"applications":[13],"for":[14,43],"deeper":[15],"semantic":[16],"understandings.":[17],"The":[18],"objective":[19],"to":[21,64,91],"extract":[22],"complete":[23],"sentences":[24,92],"the":[26,34,87],"into":[29],"a":[30,60,69,127],"txt":[31],"file":[32],"with":[33,102],"original":[35],"sentence":[36],"flow":[37],"and":[38,53,58,79,85,93,116,124],"paragraph":[39],"boundaries.":[40],"Existing":[41],"tools":[42],"extracting":[44,110,114],"PDF":[47,130],"would":[49],"often":[50],"mix":[51],"nonbody":[54,73],"texts.":[55],"We":[56,95],"devise":[57],"implement":[59],"system":[61],"called":[62],"PDFBoT":[63,98],"detect":[65],"multiple-column":[66],"layouts":[67],"using":[68,75],"line-sweeping":[70],"technique,":[71],"remove":[72],"computed":[76],"features":[78],"syntactic":[80],"tagging":[81],"backward":[83],"traversal,":[84],"align":[86],"remaining":[88],"back":[90],"paragraphs.":[94],"show":[96],"that":[97],"highly":[100],"accurate":[101],"average":[103],"F1":[104],"scores":[105],"of,":[106],"respectively,":[107],"0.99":[108],"on":[109,113,118,121],"sentences,":[111],"0.96":[112],"paragraphs,":[115],"0.98":[117],"removing":[119],"tables,":[122],"figures,":[123],"charts":[125],"over":[126],"corpus":[128],"randomly":[132],"selected":[133],"arXiv.org":[135],"across":[136],"multiple":[137],"disciplines.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}