{"id":"https://openalex.org/W4412887706","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1128","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","display_name":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887706","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1128"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1128","pdf_url":"https://aclanthology.org/2025.findings-acl.1128.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.1128.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009277091","display_name":"Zichao Li","orcid":"https://orcid.org/0000-0003-2582-3006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zichao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114352439","display_name":"Aizier Abulaiti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aizier Abulaiti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100585978","display_name":"Yaojie Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaojie Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071707350","display_name":"Xuanang Chen","orcid":"https://orcid.org/0000-0003-0377-8451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010594849","display_name":"Zheng Jia","orcid":"https://orcid.org/0000-0001-8459-515X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090777164","display_name":"Hongyu Lin","orcid":"https://orcid.org/0009-0001-5857-9663"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620300","display_name":"Xianpei Han","orcid":"https://orcid.org/0000-0002-1304-6302"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianpei Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103049525","display_name":"Shanshan Jiang","orcid":"https://orcid.org/0000-0003-0668-1954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanshan Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035683291","display_name":"Bin Dong","orcid":"https://orcid.org/0000-0003-1295-3362"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108356943","display_name":"Le Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le Sun","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":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21889","last_page":"21905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.984499990940094,"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":0.984499990940094,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9294000267982483,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7946808338165283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813780307769775},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.534460186958313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4561426639556885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3362889289855957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32551467418670654},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0751117467880249}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7946808338165283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813780307769775},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.534460186958313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4561426639556885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3362889289855957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32551467418670654},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0751117467880249},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1128","pdf_url":"https://aclanthology.org/2025.findings-acl.1128.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1128","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1128","pdf_url":"https://aclanthology.org/2025.findings-acl.1128.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":[{"id":"https://openalex.org/G160098265","display_name":null,"funder_award_id":"202401","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887706.pdf","grobid_xml":"https://content.openalex.org/works/W4412887706.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"Document":[0],"Structured":[1],"Extraction":[2],"(DSE)":[3],"aims":[4],"to":[5,32,101],"extract":[6],"structured":[7],"content":[8],"from":[9,75,81],"raw":[10],"documents.Despite":[11],"the":[12,25,125,131,137],"emergence":[13],"of":[14,46,63,106,113],"numerous":[15],"DSE":[16,47,58,90,108,134],"systems,":[17,48],"their":[18],"unified":[19,104],"evaluation":[20,45,105],"remains":[21],"inadequate,":[22],"significantly":[23],"hindering":[24],"field's":[26],"advancement.This":[27],"problem":[28],"is":[29,73],"largely":[30],"attributed":[31],"existing":[33],"benchmark":[34,53],"paradigms,":[35],"which":[36,56],"exhibit":[37],"fragmented":[38],"and":[39,78,84,98,119,130,152],"localized":[40],"characteristics.To":[41],"offer":[42],"a":[43,51,60,89,103,111],"thorough":[44],"we":[49,87,123],"introduce":[50],"novel":[52],"named":[54],"READOC,":[55],"defines":[57],"as":[59],"realistic":[61,133],"task":[62],"converting":[64],"unstructured":[65],"PDFs":[66],"into":[67],"semantically":[68],"rich":[69],"Markdown.The":[70],"READOC":[71,142],"dataset":[72],"derived":[74],"3,576":[76],"diverse":[77],"real-world":[79],"documents":[80],"arXiv,":[82],"GitHub,":[83],"Zenodo.In":[85],"addition,":[86],"develop":[88],"Evaluation":[91],"S":[92],"3":[93],"uite":[94],"comprising":[95],"Standardization,":[96],"Segmentation":[97],"Scoring":[99],"modules,":[100],"conduct":[102],"state-of-theart":[107],"approaches.By":[109],"evaluating":[110],"range":[112],"pipeline":[114],"tools,":[115],"expert":[116],"visual":[117],"models,":[118],"general":[120],"Vision-Language":[121],"Models,":[122],"identify":[124],"gap":[126],"between":[127],"current":[128],"work":[129],"unified,":[132],"objective":[135],"for":[136],"first":[138],"time.We":[139],"aspire":[140],"that":[141],"will":[143],"catalyze":[144],"future":[145],"research":[146],"in":[147],"DSE,":[148],"fostering":[149],"more":[150],"comprehensive":[151],"practical":[153],"solutions.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}