{"id":"https://openalex.org/W4406860183","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848851","title":"GVDIE: A Zero-Shot Generative Information Extraction Method for Visual Documents Based on Large Language Models","display_name":"GVDIE: A Zero-Shot Generative Information Extraction Method for Visual Documents Based on Large Language Models","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406860183","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848851"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5063885847","display_name":"Senmao Qi","orcid":"https://orcid.org/0009-0000-8048-2166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyang Qi","raw_affiliation_strings":["State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455727","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-1766-288X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100552674","display_name":"Hongzhi Sun","orcid":"https://orcid.org/0009-0004-4484-4843"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongzhi Sun","raw_affiliation_strings":["State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036444340","display_name":"Ge Yang","orcid":"https://orcid.org/0000-0003-4866-5899"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Ge","raw_affiliation_strings":["State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Shandong Electric Power Company Dezhou Power Supply Company,Dezhou,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041909892","display_name":"Bo Xiao","orcid":"https://orcid.org/0000-0001-9361-4340"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xiao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6895,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81326594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9889000058174133,"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":0.9889000058174133,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9804999828338623,"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/T10028","display_name":"Topic Modeling","score":0.9799000024795532,"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":0.7929677367210388},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6650645732879639},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6631864309310913},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6458791494369507},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6053464412689209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5880299806594849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5600482225418091},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4533211886882782},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11495962738990784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929677367210388},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6650645732879639},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6631864309310913},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6458791494369507},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6053464412689209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5880299806594849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5600482225418091},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4533211886882782},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11495962738990784},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":14,"referenced_works":["https://openalex.org/W2078777599","https://openalex.org/W2951692098","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3161879169","https://openalex.org/W3176851559","https://openalex.org/W3182680257","https://openalex.org/W4221167941","https://openalex.org/W4304013646","https://openalex.org/W4385574075","https://openalex.org/W4389524198","https://openalex.org/W4404782234","https://openalex.org/W6772827613","https://openalex.org/W6803817551"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Document":[0,30],"Information":[1,31],"Extraction":[2,32],"aims":[3],"to":[4,76],"extract":[5],"entities":[6],"and":[7,18,66,85],"relationships":[8],"from":[9,72],"visually":[10],"rich":[11],"documents.":[12,91],"Traditional":[13],"methods":[14],"require":[15],"significant":[16],"annotation":[17],"lack":[19],"generality.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"propose":[25],"GVDIE,":[26],"a":[27,57,77],"Generative":[28],"Visual":[29],"method":[33,44],"that":[34],"leverages":[35],"large":[36],"language":[37],"models":[38],"for":[39,61],"zero-shot":[40],"information":[41,70],"extraction.":[42],"This":[43,80],"aligns":[45],"document-level":[46],"multimodal":[47],"features":[48,65],"with":[49],"text":[50,63],"layout":[51,58],"features,":[52],"enhancing":[53],"performance.":[54],"We":[55],"introduce":[56],"augment":[59],"module":[60],"key":[62],"block":[64],"transform":[67],"the":[68],"document":[69],"extraction":[71],"sequence":[73],"labeling":[74],"task":[75],"generative":[78],"one.":[79],"approach":[81],"improves":[82],"flexibility,":[83],"efficiency,":[84],"adaptability":[86],"in":[87],"processing":[88],"diverse,":[89],"unstructured":[90]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}