{"id":"https://openalex.org/W4416018124","doi":"https://doi.org/10.1145/3746252.3761609","title":"From Rules to Flexibility: A Resource and Method for SEC Item Extraction in Post-2021 10-K Filings","display_name":"From Rules to Flexibility: A Resource and Method for SEC Item Extraction in Post-2021 10-K Filings","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W4416018124","doi":"https://doi.org/10.1145/3746252.3761609"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746252.3761609","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034379414","display_name":"Xiao Li","orcid":"https://orcid.org/0009-0005-6418-2354"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Xiao Li","raw_affiliation_strings":["University College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0009-0005-6418-2354","affiliations":[{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021154666","display_name":"Changhong Jin","orcid":"https://orcid.org/0000-0003-2565-592X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Changhong Jin","raw_affiliation_strings":["University College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0003-2565-592X","affiliations":[{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009000289","display_name":"Ruihai Dong","orcid":"https://orcid.org/0000-0002-2509-1370"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ruihai Dong","raw_affiliation_strings":["University College Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-2509-1370","affiliations":[{"raw_affiliation_string":"University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034379414"],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":6.9105,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96809235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6451","last_page":"6455"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.3856000006198883,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.3856000006198883,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13794","display_name":"Financial Reporting and XBRL","score":0.26019999384880066,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.12890000641345978,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5310999751091003},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43070000410079956},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.40560001134872437},{"id":"https://openalex.org/keywords/volatility","display_name":"Volatility (finance)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3522999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910000085830688},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6039999723434448},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C91602232","wikidata":"https://www.wikidata.org/wiki/Q756115","display_name":"Volatility (finance)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C98014903","wikidata":"https://www.wikidata.org/wiki/Q832161","display_name":"Financial ratio","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746252.3761609","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746252.3761609","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3259019331","display_name":null,"funder_award_id":"12/RC/2289_P2","funder_id":"https://openalex.org/F4320331354","funder_display_name":"Insight SFI Research Centre for Data Analytics"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320331354","display_name":"Insight SFI Research Centre for Data Analytics","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2295598076","https://openalex.org/W2511832088","https://openalex.org/W2625464253","https://openalex.org/W2810156540","https://openalex.org/W2963697626","https://openalex.org/W2968339949","https://openalex.org/W2981089724","https://openalex.org/W2999135213","https://openalex.org/W3092415316","https://openalex.org/W3112367847","https://openalex.org/W3126141938","https://openalex.org/W3163585381","https://openalex.org/W3209358303","https://openalex.org/W3211639606","https://openalex.org/W3212081735","https://openalex.org/W4206606391","https://openalex.org/W4206729293","https://openalex.org/W4322504035"],"related_works":[],"abstract_inverted_index":{"10-K":[0,38,71,154],"filings":[1,72],"represent":[2],"a":[3,46,76,113,125],"significant":[4],"repository":[5],"for":[6],"financial":[7,55],"text":[8,18],"analysis,":[9],"encompassing":[10],"both":[11],"standardized":[12,77],"quantitative":[13],"indicators":[14],"and":[15,61,94,156],"rich":[16],"unstructured":[17],"content.":[19],"In":[20,41],"recent":[21,70],"years,":[22],"the":[23,37,99,129,132,142],"efficacy":[24],"of":[25,54,98,110,128,131],"rule-based":[26],"extraction":[27,108],"methods":[28],"has":[29,66],"been":[30,67],"progressively":[31],"limited":[32],"due":[33],"to":[34,91,119,140],"changes":[35],"in":[36,69,75,89],"filing":[39],"format.":[40],"this":[42],"study,":[43],"we":[44],"propose":[45],"novel":[47],"layout-robust":[48],"segmentation":[49],"approach":[50,65,104],"that":[51,102],"achieves":[52,105],"identification":[53],"report":[56],"by":[57],"combining":[58],"fuzzy":[59],"matching":[60],"structural":[62],"heuristics.":[63],"Our":[64,164],"employed":[68],"(2021-2024),":[73],"resulting":[74],"dataset":[78],"with":[79,149],"item-level":[80],"segmentation.":[81],"Furthermore,":[82],"an":[83,106],"automated":[84],"validation":[85],"protocol":[86,100],"was":[87],"developed":[88],"order":[90],"assess":[92],"coverage":[93],"ranking":[95],"consistency.":[96],"Analysis":[97],"indicates":[101],"our":[103],"average":[107],"accuracy":[109],"87.8%.":[111],"Finally,":[112],"case":[114,135,157],"study":[115,136],"utilising":[116],"Item":[117],"1A":[118],"forecast":[120],"short-term":[121],"stock":[122],"volatility":[123],"provides":[124],"practical":[126],"demonstration":[127],"application":[130],"corpus.":[133],"This":[134],"not":[137],"only":[138],"serves":[139],"validate":[141],"corpus":[143],"but":[144],"also":[145],"showcases":[146],"its":[147],"compatibility":[148],"EDGAR-CORPUS.":[150],"Code,":[151],"benchmarks,":[152],"segmented":[153],"filings,":[155],"studies":[158],"are":[159],"publicly":[160],"available":[161],"on":[162],"GitHub.":[163],"GitHub":[165],"repository:":[166],"https://github.com/johnny-xiao-li/Flex_10K":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-08T00:00:00"}