{"id":"https://openalex.org/W4401943123","doi":"https://doi.org/10.1109/tkde.2024.3443928","title":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","display_name":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4401943123","doi":"https://doi.org/10.1109/tkde.2024.3443928"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2024.3443928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3443928","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5069570508","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0000-0002-5939-007X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-5939-007X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110814145","display_name":"Yonghong Song","orcid":"https://orcid.org/0000-0001-5978-3781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Song","raw_affiliation_strings":["School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-5978-3781","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383954","display_name":"Boyu Wang","orcid":"https://orcid.org/0000-0002-6108-3589"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Boyu Wang","raw_affiliation_strings":["Department of Computer Science, Brain Mind Institute, University of Western Ontario, London, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-6108-3589","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brain Mind Institute, University of Western Ontario, London, ON, Canada","institution_ids":["https://openalex.org/I125749732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113352625","display_name":"Jiaohao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaohao Liu","raw_affiliation_strings":["School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-5127-2055","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115781234","display_name":"Qi Zhang","orcid":"https://orcid.org/0009-0004-8365-740X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0004-8365-740X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77208609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"12","first_page":"9025","last_page":"9036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9986000061035156,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9692999720573425,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9574999809265137,"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":0.8158231973648071},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.6472440361976624},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6334512233734131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5102567672729492},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4783686697483063},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4294169843196869},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3567965626716614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158231973648071},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.6472440361976624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6334512233734131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5102567672729492},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4783686697483063},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4294169843196869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3567965626716614},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2024.3443928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2024.3443928","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1984591968","display_name":null,"funder_award_id":"61973245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1984685202","https://openalex.org/W2024665095","https://openalex.org/W2038484192","https://openalex.org/W2061873838","https://openalex.org/W2891117443","https://openalex.org/W2895094948","https://openalex.org/W2933138175","https://openalex.org/W2964159205","https://openalex.org/W2971296908","https://openalex.org/W2972985407","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3009561768","https://openalex.org/W3035335952","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3100906513","https://openalex.org/W3104953317","https://openalex.org/W3118608800","https://openalex.org/W3163650427","https://openalex.org/W3171007011","https://openalex.org/W3173306993","https://openalex.org/W3173783447","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3180562345","https://openalex.org/W3182680257","https://openalex.org/W3190448953","https://openalex.org/W3197579463","https://openalex.org/W3198984549","https://openalex.org/W3200439183","https://openalex.org/W3209059054","https://openalex.org/W4221162144","https://openalex.org/W4280634279","https://openalex.org/W4295832380","https://openalex.org/W4365790188","https://openalex.org/W6638523607","https://openalex.org/W6676984168","https://openalex.org/W6681588610","https://openalex.org/W6682948231","https://openalex.org/W6717772578","https://openalex.org/W6733814495","https://openalex.org/W6762913911","https://openalex.org/W6764124961","https://openalex.org/W6765939562","https://openalex.org/W6768033458","https://openalex.org/W6772827613","https://openalex.org/W6773005947","https://openalex.org/W6774670964","https://openalex.org/W6779101013","https://openalex.org/W6780218876","https://openalex.org/W6781063151","https://openalex.org/W6787972765","https://openalex.org/W6791353385","https://openalex.org/W6797119129","https://openalex.org/W6802864417","https://openalex.org/W6839041728","https://openalex.org/W6842024468","https://openalex.org/W6849385481"],"related_works":["https://openalex.org/W2355499516","https://openalex.org/W3210974833","https://openalex.org/W2599000612","https://openalex.org/W2811475781","https://openalex.org/W2094246381","https://openalex.org/W2361137193","https://openalex.org/W2377736761","https://openalex.org/W2353928006","https://openalex.org/W2797910360","https://openalex.org/W3123951377"],"abstract_inverted_index":{"Document":[0],"key":[1],"information":[2,122],"extraction":[3],"(DKIE)":[4],"methods":[5],"often":[6],"require":[7],"a":[8,77,137],"large":[9],"number":[10],"of":[11,55,93,116,123,129,161],"labeled":[12,37,132,236],"samples,":[13,237],"imposing":[14],"substantial":[15],"annotation":[16],"costs":[17],"in":[18,49,58],"practical":[19],"scenarios.":[20],"Fortunately,":[21],"pseudo-labeling":[22],"based":[23],"semi-supervised":[24,84],"learning":[25],"(PSSL)":[26],"algorithms":[27],"provide":[28],"an":[29],"effective":[30],"paradigm":[31],"to":[32,112,146,175,191,243],"alleviate":[33,152,193],"the":[34,44,91,103,114,120,127,168,184,198,217,244],"reliance":[35],"on":[36,69,95,155,197,204,230],"data":[38,125],"by":[39,220],"leveraging":[40],"unlabeled":[41,134],"data.":[42,135],"However,":[43],"main":[45],"challenges":[46],"for":[47,86],"PSSL":[48],"DKIE":[50,56,87,96,124,156],"tasks:":[51],"1)":[52],"context":[53],"dependency":[54],"results":[57,203],"incorrect":[59],"pseudo-labels.":[60],"2)":[61],"high":[62],"intra-class":[63,149,169,178],"variance":[64,150,195],"and":[65,133,151,213,232],"low":[66],"inter-class":[67,153,185,194],"variation":[68,154],"DKIE.":[70],"To":[71],"this":[72,74],"end,":[73],"paper":[75],"proposes":[76],"similarity":[78,130],"matrix":[79],"Pseudo-Label":[80],"Bias":[81,106],"Rectification":[82,107],"(PLBR)":[83],"method":[85],"tasks,":[88],"which":[89,118,158,172,188],"improves":[90],"quality":[92,115],"pseudo-labels":[94],"benchmarks":[97,206],"with":[98,234],"rare":[99,235],"labels.":[100],"More":[101],"specifically,":[102],"Similarity":[104],"Matrix":[105],"(SMBR)":[108],"module":[109],"is":[110,144,159,167,173,183,189],"proposed":[111],"improve":[113],"pseudo-labels,":[117],"utilizes":[119],"contextual":[121],"through":[126],"analysis":[128],"between":[131],"Moreover,":[136],"dual":[138],"branch":[139],"adaptive":[140,163],"alignment":[141,164,170,186],"(DBAA)":[142],"mechanism":[143],"designed":[145,174],"adaptively":[147,176,192],"align":[148,177],"benchmarks,":[157],"composed":[160],"two":[162,205],"ways.":[165],"One":[166],"branch,":[171,187],"variance.":[179],"The":[180],"other":[181],"one":[182],"developed":[190],"changes":[196],"representation":[199],"level.":[200],"Extensive":[201],"experiment":[202],"demonstrate":[207],"that":[208],"PLBR":[209],"achieves":[210],"state-of-the-art":[211],"performance":[212,215],"its":[214],"surpasses":[216],"previous":[218],"SOTA":[219],"<inline-formula><tex-math":[221,225],"notation=\"LaTeX\">$2.11\\%":[222],"\\sim":[223,227],"2.53\\%$</tex-math></inline-formula>,":[224],"notation=\"LaTeX\">$2.09\\%":[226],"2.49\\%$</tex-math></inline-formula>":[228],"F1-score":[229],"FUNSD":[231],"CORD":[233],"respectively.":[238],"Code":[239],"will":[240],"be":[241],"open":[242],"public.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}