{"id":"https://openalex.org/W2062855923","doi":"https://doi.org/10.1108/02640470810851743","title":"Converting PDF files to XML files","display_name":"Converting PDF files to XML files","publication_year":2008,"publication_date":"2008-02-09","ids":{"openalex":"https://openalex.org/W2062855923","doi":"https://doi.org/10.1108/02640470810851743","mag":"2062855923"},"language":"en","primary_location":{"id":"doi:10.1108/02640470810851743","is_oa":false,"landing_page_url":"https://doi.org/10.1108/02640470810851743","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101462549","display_name":"Wende Zhang","orcid":"https://orcid.org/0000-0002-6293-5093"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wende Zhang","raw_affiliation_strings":["Fuzhou University Library, Fuzhou, Fujian, People's Republic of China","(Fuzhou University Library, Fuzhou, Fujian, People's Republic of China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University Library, Fuzhou, Fujian, People's Republic of China","institution_ids":["https://openalex.org/I80947539"]},{"raw_affiliation_string":"(Fuzhou University Library, Fuzhou, Fujian, People's Republic of China)","institution_ids":["https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101462549"],"corresponding_institution_ids":["https://openalex.org/I80947539"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.12233951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":"1","first_page":"68","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8657100796699524},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6422602534294128},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5263394117355347},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.523297131061554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5230641961097717},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5079753994941711},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4839909076690674},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.4637748599052429},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.44283533096313477},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.270853728055954},{"id":"https://openalex.org/keywords/versioning-file-system","display_name":"Versioning file system","score":0.17240020632743835},{"id":"https://openalex.org/keywords/stub-file","display_name":"Stub file","score":0.11338338255882263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657100796699524},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6422602534294128},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5263394117355347},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.523297131061554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5230641961097717},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5079753994941711},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4839909076690674},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.4637748599052429},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.44283533096313477},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.270853728055954},{"id":"https://openalex.org/C166807848","wikidata":"https://www.wikidata.org/wiki/Q3445065","display_name":"Versioning file system","level":4,"score":0.17240020632743835},{"id":"https://openalex.org/C13674803","wikidata":"https://www.wikidata.org/wiki/Q7627301","display_name":"Stub file","level":3,"score":0.11338338255882263}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1108/02640470810851743","is_oa":false,"landing_page_url":"https://doi.org/10.1108/02640470810851743","pdf_url":null,"source":{"id":"https://openalex.org/S902750600","display_name":"The Electronic Library","issn_l":"0264-0473","issn":["0264-0473","1758-616X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Electronic Library","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2160196229"],"related_works":["https://openalex.org/W2793346709","https://openalex.org/W2090798606","https://openalex.org/W1923701591","https://openalex.org/W2368195534","https://openalex.org/W3032858184","https://openalex.org/W4388155196","https://openalex.org/W2067129367","https://openalex.org/W2162753096","https://openalex.org/W2563780781","https://openalex.org/W2071204444"],"abstract_inverted_index":{"Purpose":[0],"The":[1,20,37,89,154],"purpose":[2],"of":[3,171],"this":[4,94,146],"paper":[5,47,147,160],"is":[6,39,77,131],"to":[7,16,50,80,92,101,107,120,133,136,165],"develop":[8],"a":[9,43,51,108],"system":[10,21,98],"that":[11],"can":[12,115,151,161],"convert":[13,102],"PDF":[14,49,58,86,104,143],"files":[15,144],"XML":[17,24,53],"files.":[18,172],"Design/methodology/approach":[19],"works":[22],"with":[23,126],"as":[25,32],"an":[26,33],"information":[27,34,66,70,83,141,166],"display":[28,69],"model":[29],"and":[30,45,67,138,145],"XSLT":[31],"extraction":[35,167],"rule.":[36],"process":[38],"illustrated":[40],"by":[41],"converting":[42],"scientific":[44],"technological":[46],"in":[48,72,96,124,158],"valid":[52],"file.":[54,88],"Findings":[55],"Because":[56],"the":[57,61,68,85,97,103,121,159],"file":[59,106,123],"adopts":[60],"self\u2010descriptive":[62],"definition,":[63],"its":[64],"content":[65],"exists":[71],"different":[73],"objects;":[74],"therefore,":[75],"it":[76,150],"not":[78],"easy":[79,110],"directly":[81],"extract":[82,140],"from":[84,142,168],"source":[87,105],"undirected":[90],"way":[91],"solve":[93],"problem":[95],"design":[99,155],"was":[100],"relatively":[109],"processing":[111],"intermediate":[112],"format,":[113],"which":[114],"then":[116],"be":[117,134,152,163],"automatically":[118],"converted":[119],"target":[122],"accordance":[125],"relevant":[127],"rules.":[128],"Originality/value":[129],"It":[130],"important":[132],"able":[135],"easily":[137],"conveniently":[139],"shows":[148],"how":[149],"done.":[153],"ideas":[156],"contained":[157],"also":[162],"applied":[164],"other":[169],"types":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
