{"id":"https://openalex.org/W4394683350","doi":"https://doi.org/10.1145/3657299","title":"FETILDA: Evaluation Framework for Effective Representations of Long Financial Documents","display_name":"FETILDA: Evaluation Framework for Effective Representations of Long Financial Documents","publication_year":2024,"publication_date":"2024-04-10","ids":{"openalex":"https://openalex.org/W4394683350","doi":"https://doi.org/10.1145/3657299"},"language":"en","primary_location":{"id":"doi:10.1145/3657299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657299","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3657299","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046237209","display_name":"Bolun Xia","orcid":"https://orcid.org/0000-0001-6841-9017"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolun (Namir) Xia","raw_affiliation_strings":["Rensselaer Polytechnic Institute School of Science, Troy, United States","Computer Science Rensselaer Polytechnic Institute School of Science, Troy, USA"],"raw_orcid":"https://orcid.org/0000-0001-6841-9017","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute School of Science, Troy, United States","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Computer Science Rensselaer Polytechnic Institute School of Science, Troy, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065241005","display_name":"Vipula Rawte","orcid":"https://orcid.org/0000-0002-4355-1393"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipula Rawte","raw_affiliation_strings":["Rensselaer Polytechnic Institute School of Science, Troy, United States","Computer Science Rensselaer Polytechnic Institute School of Science, Troy, USA"],"raw_orcid":"https://orcid.org/0000-0002-4355-1393","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute School of Science, Troy, United States","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Computer Science Rensselaer Polytechnic Institute School of Science, Troy, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079035190","display_name":"Aparna Gupta","orcid":"https://orcid.org/0000-0002-5275-7756"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aparna Gupta","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, United States","Lally School of Management Rensselaer Polytechnic Institute, Troy, USA"],"raw_orcid":"https://orcid.org/0000-0002-5275-7756","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, United States","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Lally School of Management Rensselaer Polytechnic Institute, Troy, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019559411","display_name":"Mohammed J. Zaki","orcid":"https://orcid.org/0000-0003-4711-0234"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Zaki","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, United States","Department of Computer Science Rensselaer Polytechnic Institute, Troy, USA"],"raw_orcid":"https://orcid.org/0000-0003-4711-0234","affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, United States","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Department of Computer Science Rensselaer Polytechnic Institute, Troy, USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79996411,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"18","issue":"7","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8294020891189575},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5266323685646057},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5144655704498291},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48754045367240906},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.4463443458080292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44058066606521606},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41754794120788574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41488566994667053},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4129818379878998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3806692361831665},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35111159086227417},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32441282272338867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294020891189575},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5266323685646057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5144655704498291},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48754045367240906},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.4463443458080292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44058066606521606},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41754794120788574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41488566994667053},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4129818379878998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3806692361831665},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35111159086227417},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32441282272338867},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3657299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657299","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3657299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3657299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3657299","source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G7107011861","display_name":"IUCRC Phase I RPI: Center for Research toward Advancing Financial Technologies (CRAFT)","funder_award_id":"2113850","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394683350.pdf","grobid_xml":"https://content.openalex.org/works/W4394683350.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W2116209939","https://openalex.org/W2250539671","https://openalex.org/W2489540272","https://openalex.org/W2492461111","https://openalex.org/W2508577255","https://openalex.org/W2511832088","https://openalex.org/W2533588933","https://openalex.org/W2890255136","https://openalex.org/W2911971986","https://openalex.org/W2951416252","https://openalex.org/W2951888662","https://openalex.org/W2963341956","https://openalex.org/W2964081769","https://openalex.org/W2969112234","https://openalex.org/W2981852735","https://openalex.org/W2990138404","https://openalex.org/W3019932981","https://openalex.org/W3023787414","https://openalex.org/W3035101152","https://openalex.org/W3035391452","https://openalex.org/W3093838622","https://openalex.org/W3104328696","https://openalex.org/W3105238007","https://openalex.org/W3122309589","https://openalex.org/W3122563224","https://openalex.org/W3125952890","https://openalex.org/W3153712169","https://openalex.org/W3173365702","https://openalex.org/W4206045084","https://openalex.org/W4232619139","https://openalex.org/W4288089799","https://openalex.org/W4298110867","https://openalex.org/W4300485781","https://openalex.org/W4380373983","https://openalex.org/W4382998379","https://openalex.org/W6941258058"],"related_works":["https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3157284875","https://openalex.org/W2147241511","https://openalex.org/W2259406085","https://openalex.org/W3113264705","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W3090872036"],"abstract_inverted_index":{"In":[0,82,168],"the":[1,15,31,108,131,148,151,221,267],"financial":[2,11],"sphere,":[3],"there":[4,85],"is":[5,54,61],"a":[6,23,50,175,182,199],"wealth":[7],"of":[8,63,103,111,133,150,153,196,201,212,223,226,269,271],"accumulated":[9],"unstructured":[10],"data,":[12],"such":[13,29],"as":[14,30,124,126,241,243],"textual":[16,73,104,163,239,272],"disclosure":[17],"documents":[18,37,164,264],"that":[19,53,180],"companies":[20],"submit":[21],"on":[22,142,198],"regular":[24],"basis":[25],"to":[26,44,66,118,218],"regulatory":[27],"agencies,":[28],"Securities":[32],"and":[33,42,173,209,257],"Exchange":[34],"Commission.":[35],"These":[36],"are":[38],"typically":[39],"very":[40],"long":[41,72,122,162,263],"tend":[43],"contain":[45],"valuable":[46],"soft":[47,159],"information":[48,160],"about":[49],"company\u2019s":[51],"performance":[52,80,222],"not":[55],"present":[56],"in":[57,90,156,277],"quantitative":[58],"predictors.":[59],"It":[60],"therefore":[62],"great":[64,88],"interest":[65],"learn":[67],"predictive":[68,279],"models":[69,97],"from":[70,100,161],"these":[71],"documents,":[74,123],"especially":[75],"for":[76,121,165,238,244,261],"forecasting":[77],"numerical":[78,245],"key":[79],"indicators.":[81],"recent":[83],"years,":[84],"has":[86],"been":[87],"progress":[89],"natural":[91],"language":[92,96,227],"processing":[93],"via":[94],"pre-trained":[95,255],"(LMs)":[98],"learned":[99],"large":[101],"corpora":[102],"data.":[105],"This":[106],"prompts":[107],"important":[109],"question":[110],"whether":[112],"they":[113],"can":[114,129,265],"be":[115],"used":[116],"effectively":[117],"produce":[119],"representations":[120,134],"well":[125,242],"how":[127,253],"we":[128,171],"evaluate":[130],"effectiveness":[132],"produced":[135],"by":[136,206,215],"various":[137,154],"LMs.":[138],"Our":[139,247],"work":[140,248],"focuses":[141],"answering":[143],"this":[144,169],"critical":[145],"question,":[146],"namely,":[147],"evaluation":[149,178],"efficacy":[152],"LMs":[155,233,260],"extracting":[157],"useful":[158],"prediction":[166],"tasks.":[167],"article,":[170],"propose":[172],"implement":[174],"deep":[176],"learning":[177],"framework":[179,231],"utilizes":[181],"sequential":[183],"chunking":[184],"approach":[185],"combined":[186],"with":[187],"an":[188,193],"attention":[189],"mechanism.":[190],"We":[191],"perform":[192],"extensive":[194],"set":[195],"experiments":[197],"collection":[200],"10-K":[202],"reports":[203,213],"submitted":[204,214],"annually":[205],"U.S.":[207,216],"banks,":[208],"another":[210],"dataset":[211],"companies,":[217],"investigate":[219],"thoroughly":[220],"different":[224],"types":[225],"models.":[228],"Overall,":[229],"our":[230],"using":[232],"outperforms":[234],"strong":[235],"baseline":[236],"methods":[237],"modeling":[240],"regression.":[246],"provides":[249],"better":[250],"insights":[251],"into":[252],"utilizing":[254],"domain-specific":[256],"fine-tuned":[258],"long-input":[259],"representing":[262],"improve":[266],"quality":[268],"representation":[270],"data":[273],"and,":[274],"therefore,":[275],"help":[276],"improving":[278],"analyses.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}