{"id":"https://openalex.org/W4412887942","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1075","title":"PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction","display_name":"PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887942","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1075"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1075","pdf_url":"https://aclanthology.org/2025.findings-acl.1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1075.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004068693","display_name":"Birgit Kirsch","orcid":"https://orcid.org/0000-0002-4888-4947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Birgit Kirsch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043402158","display_name":"H\u00e9ctor Allende\u2010Cid","orcid":"https://orcid.org/0000-0003-3047-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e9ctor Allende-Cid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003150215","display_name":"Stefan Rueping","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Rueping","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83321777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"20890","last_page":"20912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9955000281333923,"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":0.9955000281333923,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9760000109672546,"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/T10028","display_name":"Topic Modeling","score":0.9714000225067139,"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/key","display_name":"Key (lock)","score":0.7605044841766357},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7219180464744568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117000222206116},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7050455808639526},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5956703424453735},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47953033447265625},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.46525058150291443},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4112872779369354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35638192296028137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08010914921760559},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07403352856636047}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7605044841766357},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7219180464744568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117000222206116},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7050455808639526},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5956703424453735},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47953033447265625},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.46525058150291443},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4112872779369354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35638192296028137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08010914921760559},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07403352856636047},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1075","pdf_url":"https://aclanthology.org/2025.findings-acl.1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/497467","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/497467","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1075","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1075","pdf_url":"https://aclanthology.org/2025.findings-acl.1075.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887942.pdf","grobid_xml":"https://content.openalex.org/works/W4412887942.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2002739602","https://openalex.org/W1968042686","https://openalex.org/W2897881820","https://openalex.org/W2345647014","https://openalex.org/W2201192772","https://openalex.org/W2161960196","https://openalex.org/W3136891595","https://openalex.org/W1964819397"],"abstract_inverted_index":{"Key":[0],"Information":[1,116],"Extraction":[2,117],"(KIE)":[3,118],"from":[4,125],"visually":[5,126],"rich":[6,127],"documents":[7,128,198],"is":[8,146],"commonly":[9],"approached":[10,212],"as":[11,53,156,217],"either":[12],"fine-grained":[13],"token":[14],"classification":[15],"or":[16,202],"coarse-grained":[17,50],"entity":[18],"extraction.While":[19],"tokenlevel":[20],"models":[21,28,80,101],"capture":[22],"spatial":[23],"and":[24,33,49,62,76,93,102,158,183],"visual":[25],"cues,":[26],"entity-level":[27],"better":[29],"represent":[30],"logical":[31,74],"dependencies":[32],"align":[34],"with":[35,199],"real-world":[36],"use":[37],"cases.We":[38],"introduce":[39],"PM3-KIE,":[40],"a":[41,54,66,103,107,136,167],"probabilistic":[42],"multitask":[43],"meta-model":[44],"that":[45,58,96,139],"incorporates":[46,68],"both":[47],"finegrained":[48],"models.It":[51],"serves":[52],"lightweight":[55],"reasoning":[56],"layer":[57],"jointly":[59],"predicts":[60],"entities":[61],"all":[63],"appearances":[64],"in":[65,112,219],"document.PM3-KIE":[67],"domain-specific":[69],"schema":[70,138],"constraints":[71],"to":[72,177],"enforce":[73],"consistency":[75],"integrates":[77],"large":[78],"language":[79],"for":[81,148,170,193,197],"semantic":[82],"validation,":[83],"thereby":[84],"reducing":[85],"extraction":[86,161],"errors.Experiments":[87],"on":[88,120,135],"two":[89,214],"public":[90],"datasets,":[91],"DeepForm":[92],"FARA,":[94],"show":[95],"PM3-KIE":[97],"outperforms":[98],"three":[99],"state-of-the-art":[100,194],"stacked":[104],"ensemble,":[105],"achieving":[106],"statistically":[108],"significant":[109],"2%":[110],"improvement":[111],"F1":[113],"score.":[114],"IntroductionKey":[115],"focuses":[119],"identifying":[121],"structured":[122,189],"key-value":[123],"pairs":[124],"(VRDs)":[129],"(Huang":[130],"et":[131,206],"al.,":[132,207],"2019)":[133],"based":[134],"predefined":[137],"specifies":[140],"the":[141],"target":[142],"information":[143,160],"types.This":[144],"capability":[145],"essential":[147],"automating":[149],"business":[150],"document":[151],"processing":[152,166],"across":[153],"industries":[154],"such":[155],"finance":[157],"law.Automating":[159],"significantly":[162],"reduces":[163],"operational":[164],"costs:":[165],"single":[168],"invoice,":[169],"example,":[171],"can":[172,209],"cost":[173],"$13.11and":[174],"takes":[175],"up":[176],"eight":[178],"days":[179],"(Girsch-Bock,":[180],"Mary,":[181],"2024;Cohen":[182],"York,":[184],"2020).Despite":[185],"recent":[186],"advances,":[187],"extracting":[188],"data":[190],"remains":[191],"challenging":[192],"models,":[195],"particularly":[196],"complex":[200],"schemas":[201],"semi-structured":[203],"layouts":[204],"(Wang":[205],"2023b).KIE":[208],"generally":[210],"be":[211],"through":[213],"distinct":[215],"paradigms,":[216],"illustrated":[218],"Figure":[220],"1:":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}