{"id":"https://openalex.org/W4403791487","doi":"https://doi.org/10.1145/3664647.3680931","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","display_name":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791487","doi":"https://doi.org/10.1145/3664647.3680931"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680931","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680931","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5024815485","display_name":"Zening Lin","orcid":"https://orcid.org/0000-0002-5827-0594"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zening Lin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-8681-311X","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038186072","display_name":"Jiapeng Wang","orcid":"https://orcid.org/0000-0002-2060-3488"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiapeng Wang","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2060-3488","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Teng Li","orcid":"https://orcid.org/0009-0008-5852-7960"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Li","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-5852-7960","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079914128","display_name":"Wenhui Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Liao","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-3823-0132","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048985850","display_name":"Dayi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108461","display_name":"Kingsoft (China)","ror":"https://ror.org/01stnfn33","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210108461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dayi Huang","raw_affiliation_strings":["Kingsoft Office, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0002-8248-2906","affiliations":[{"raw_affiliation_string":"Kingsoft Office, Zhuhai, China","institution_ids":["https://openalex.org/I4210108461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034348457","display_name":"Longfei Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108461","display_name":"Kingsoft (China)","ror":"https://ror.org/01stnfn33","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210108461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfei Xiong","raw_affiliation_strings":["Kingsoft Office, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0000-2029-8391","affiliations":[{"raw_affiliation_string":"Kingsoft Office, Zhuhai, China","institution_ids":["https://openalex.org/I4210108461"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5456-0957","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024815485"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.8758,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88080779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5171","last_page":"5180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/extraction","display_name":"Extraction (chemistry)","score":0.6495471000671387},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.6256415843963623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5917333960533142},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5573742985725403},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3253532648086548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32462209463119507},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.12872222065925598},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12355053424835205},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07120466232299805}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6495471000671387},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.6256415843963623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5917333960533142},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5573742985725403},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3253532648086548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32462209463119507},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.12872222065925598},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12355053424835205},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07120466232299805},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680931","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680931","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2102517947","https://openalex.org/W2137959438","https://openalex.org/W2270423142","https://openalex.org/W2808142148","https://openalex.org/W2905462022","https://openalex.org/W2963613359","https://openalex.org/W2964022985","https://openalex.org/W2997154779","https://openalex.org/W3034617555","https://openalex.org/W3104953317","https://openalex.org/W3116427155","https://openalex.org/W3167136668","https://openalex.org/W3173306993","https://openalex.org/W3176851559","https://openalex.org/W3200439183","https://openalex.org/W3205981739","https://openalex.org/W3214042621","https://openalex.org/W4221167941","https://openalex.org/W4226020328","https://openalex.org/W4285105124","https://openalex.org/W4285305471","https://openalex.org/W4304013646","https://openalex.org/W4304098606","https://openalex.org/W4382202584","https://openalex.org/W4385574075","https://openalex.org/W4385990846","https://openalex.org/W4386075596","https://openalex.org/W4386075876","https://openalex.org/W4389524198","https://openalex.org/W4390873338"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W4403582721","https://openalex.org/W4400488565"],"abstract_inverted_index":{"Document":[0],"pair":[1,79,124],"extraction":[2,33,80],"aims":[3],"to":[4,44,51,112,119,140],"identify":[5],"key":[6],"and":[7,31,39,48,93,103,118,137,145,179,184,187],"value":[8],"entities":[9,56],"as":[10,12],"well":[11],"their":[13],"relationships":[14],"from":[15],"visually-rich":[16],"documents.":[17],"Most":[18],"existing":[19],"methods":[20],"divide":[21],"it":[22,49],"into":[23],"two":[24],"separate":[25],"tasks:":[26],"semantic":[27],"entity":[28,94],"recognition":[29],"(SER)":[30],"relation":[32],"(RE).":[34],"However,":[35],"simply":[36],"concatenating":[37],"SER":[38],"RE":[40],"serially":[41],"can":[42,104],"lead":[43],"severe":[45],"error":[46,100],"propagation,":[47],"fails":[50],"handle":[52,105],"cases":[53],"like":[54,177],"multi-line":[55,109],"in":[57,81],"real":[58],"scenarios.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"this":[64],"paper":[65],"introduces":[66],"a":[67,82,129,163],"novel":[68],"framework,":[69],"PEneo":[70],"(Pair":[71],"Extraction":[72],"new":[73,189],"decoder":[74],"option),":[75],"which":[76],"performs":[77],"document":[78],"unified":[83],"pipeline,":[84],"incorporating":[85],"three":[86],"concurrent":[87],"sub-tasks:":[88],"line":[89,91],"extraction,":[90,125],"grouping,":[92],"linking.":[95],"This":[96],"approach":[97],"alleviates":[98],"the":[99,106,115,133,160,188],"accumulation":[101],"problem":[102],"case":[107],"of":[108,132],"entities.":[110],"Furthermore,":[111],"better":[113],"evaluate":[114],"model's":[116],"performance":[117,161],"facilitate":[120],"future":[121],"research":[122],"on":[123,150,170],"we":[126],"introduce":[127],"RFUND,":[128],"re-annotated":[130],"version":[131],"commonly":[134],"used":[135],"FUNSD":[136],"XFUND":[138],"datasets,":[139],"make":[141],"them":[142],"more":[143],"accurate":[144],"cover":[146],"realistic":[147],"situations.":[148],"Experiments":[149],"various":[151,175],"benchmarks":[152],"demonstrate":[153],"PEneo's":[154],"superiority":[155],"over":[156],"previous":[157],"pipelines,":[158],"boosting":[159],"by":[162],"large":[164],"margin":[165],"(e.g.,":[166],"19.89%-22.91%":[167],"F1":[168],"score":[169],"RFUND-EN)":[171],"when":[172],"combined":[173],"with":[174],"backbones":[176],"LiLT":[178],"LayoutLMv3,":[180],"showing":[181],"its":[182],"effectiveness":[183],"generality.":[185],"Codes":[186],"annotations":[190],"are":[191],"available":[192],"at":[193],"https://github.com/ZeningLin/PEneo.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}