{"id":"https://openalex.org/W2572428969","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-064","title":"Information Extraction from Resume Documents in PDF Format","display_name":"Information Extraction from Resume Documents in PDF Format","publication_year":2016,"publication_date":"2016-02-17","ids":{"openalex":"https://openalex.org/W2572428969","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-064","mag":"2572428969"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-064","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-064","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","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/A5074504151","display_name":"Jiaze Chen","orcid":"https://orcid.org/0000-0002-5643-6503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaze Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangcai Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7065,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92535253,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"28","issue":"17","first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.8873000144958496,"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":0.8873000144958496,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8586999773979187,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7799000144004822,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139041662216187},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.7762763500213623},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6647792458534241},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6247627139091492},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6023057699203491},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5779006481170654},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.524284303188324},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.45830821990966797},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4504129886627197},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4149192273616791},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4038662314414978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3418418765068054},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22157099843025208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139041662216187},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.7762763500213623},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6647792458534241},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6247627139091492},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6023057699203491},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5779006481170654},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.524284303188324},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.45830821990966797},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4504129886627197},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4149192273616791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4038662314414978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418418765068054},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22157099843025208},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-064","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-064","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2888256870","https://openalex.org/W2376135541","https://openalex.org/W2394022102","https://openalex.org/W1788528807","https://openalex.org/W2725657302","https://openalex.org/W2074870855","https://openalex.org/W2393978999","https://openalex.org/W1590308178","https://openalex.org/W2153799433","https://openalex.org/W4316021222"],"abstract_inverted_index":{"Now":[0],"more":[1,3,145],"and":[2,11,58,96,111],"people":[4],"release":[5],"their":[6],"resumes":[7],"through":[8],"the":[9,49,94,102,125,128,132,142,150,154],"Internet,":[10],"PDF":[12,56,100,118],"is":[13,81],"a":[14,35,60,69,84],"wide":[15],"adopted":[16],"format":[17],"of":[18,24,93,99,108,127,149],"resume":[19,53],"documents":[20,54],"which":[21,114],"contain":[22],"lots":[23],"valuable":[25],"information":[26,98],"for":[27,141],"recruitment,":[28],"personal":[29],"profile":[30],"mining,":[31],"etc.":[32],"However,":[33],"only":[34],"few":[36],"studies":[37],"have":[38],"been":[39],"down":[40],"in":[41,55,153],"this":[42,45,66],"direction.":[43],"Therefore,":[44],"paper":[46],"focuses":[47],"on":[48],"task–information":[50],"extraction":[51,62],"from":[52,117],"format,":[57],"proposes":[59],"hierarchical":[61],"method.":[63,130],"At":[64],"first,":[65],"method":[67],"segments":[68],"page":[70],"into":[71],"blocks":[72],"according":[73],"to":[74,137],"heuristic":[75],"rules.":[76],"And":[77],"then":[78],"each":[79],"block":[80],"classified":[82],"by":[83],"Conditional":[85],"Random":[86],"Field":[87],"(CRF)":[88],"model.":[89],"To":[90],"take":[91],"advantage":[92],"structure":[95],"layout":[97],"documents,":[101],"classification":[103],"model":[104],"employs":[105],"two":[106],"kinds":[107],"features:content-based":[109],"features":[110,113,134],"layoutbased":[112],"are":[115,135],"parsed":[116],"documents.":[119],"The":[120],"experimental":[121],"results":[122],"show":[123],"that":[124],"effectiveness":[126],"proposed":[129],"Especially,":[131],"layout-based":[133],"proved":[136],"be":[138],"very":[139],"useful":[140],"task,":[143],"improving":[144],"than":[146],"20":[147],"percent":[148],"average":[151],"F1-score":[152],"experiments.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}