{"id":"https://openalex.org/W4318148222","doi":"https://doi.org/10.1109/bigdata55660.2022.10020873","title":"Named Entity Recognition in Long Documents: An End-to-end Case Study in the Legal Domain","display_name":"Named Entity Recognition in Long Documents: An End-to-end Case Study in the Legal Domain","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318148222","doi":"https://doi.org/10.1109/bigdata55660.2022.10020873"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020873","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","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/A5034042939","display_name":"Hossein Keshavarz","orcid":"https://orcid.org/0000-0002-1031-9862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hossein Keshavarz","raw_affiliation_strings":["Relational AI,Austin,USA","Relational AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Relational AI,Austin,USA","institution_ids":[]},{"raw_affiliation_string":"Relational AI, Austin, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090568937","display_name":"Zografoula Vagena","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zografoula Vagena","raw_affiliation_strings":["Relational AI,Austin,USA","Relational AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Relational AI,Austin,USA","institution_ids":[]},{"raw_affiliation_string":"Relational AI, Austin, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077023627","display_name":"Pigi Kouki","orcid":"https://orcid.org/0000-0003-3265-9080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pigi Kouki","raw_affiliation_strings":["Relational AI,Austin,USA","Relational AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Relational AI,Austin,USA","institution_ids":[]},{"raw_affiliation_string":"Relational AI, Austin, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019267320","display_name":"Ilias Fountalis","orcid":"https://orcid.org/0000-0002-7134-2062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilias Fountalis","raw_affiliation_strings":["Relational AI,Austin,USA","Relational AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Relational AI,Austin,USA","institution_ids":[]},{"raw_affiliation_string":"Relational AI, Austin, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016417535","display_name":"Mehdi Mabrouki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehdi Mabrouki","raw_affiliation_strings":["Licht Blick SE,Berlin,Germany","Licht Blick SE, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Licht Blick SE,Berlin,Germany","institution_ids":[]},{"raw_affiliation_string":"Licht Blick SE, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009396324","display_name":"Aziz Belaweid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aziz Belaweid","raw_affiliation_strings":["JinaAI,Berlin,Germany","JinaAI, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JinaAI,Berlin,Germany","institution_ids":[]},{"raw_affiliation_string":"JinaAI, Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034623242","display_name":"Nikolaos Vasiloglou","orcid":"https://orcid.org/0000-0001-8499-7781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Vasiloglou","raw_affiliation_strings":["Relational AI,Austin,USA","Relational AI, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Relational AI,Austin,USA","institution_ids":[]},{"raw_affiliation_string":"Relational AI, Austin, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69043202,"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":"2024","last_page":"2033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9934999942779541,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.8380081653594971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8179581165313721},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6601020097732544},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6239529848098755},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.591293454170227},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5743485689163208},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.5717675089836121},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5407775044441223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5327940583229065},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5250102281570435},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4745924174785614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4614931344985962},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41953763365745544},{"id":"https://openalex.org/keywords/common-ground","display_name":"Common ground","score":0.41651293635368347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3587263822555542},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.3401781916618347},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09412434697151184}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8380081653594971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179581165313721},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6601020097732544},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6239529848098755},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.591293454170227},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5743485689163208},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.5717675089836121},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5407775044441223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5327940583229065},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5250102281570435},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4745924174785614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4614931344985962},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41953763365745544},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.41651293635368347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587263822555542},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3401781916618347},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09412434697151184},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020873","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W967544008","https://openalex.org/W1513874326","https://openalex.org/W1902237438","https://openalex.org/W2004763266","https://openalex.org/W2013856010","https://openalex.org/W2121879602","https://openalex.org/W2124657827","https://openalex.org/W2133564696","https://openalex.org/W2141099517","https://openalex.org/W2296283641","https://openalex.org/W2404161646","https://openalex.org/W2766164908","https://openalex.org/W2769041395","https://openalex.org/W2785787385","https://openalex.org/W2889720216","https://openalex.org/W2908510526","https://openalex.org/W2946602766","https://openalex.org/W2959716049","https://openalex.org/W2962902328","https://openalex.org/W2965373594","https://openalex.org/W2965762238","https://openalex.org/W2966491090","https://openalex.org/W2970771982","https://openalex.org/W2990859184","https://openalex.org/W2998184481","https://openalex.org/W3003928769","https://openalex.org/W3034653145","https://openalex.org/W3037169522","https://openalex.org/W3048002659","https://openalex.org/W3088586444","https://openalex.org/W3092072817","https://openalex.org/W3099950029","https://openalex.org/W3104182623","https://openalex.org/W3105241646","https://openalex.org/W3105662186","https://openalex.org/W3111011642","https://openalex.org/W3117829624","https://openalex.org/W3174254835","https://openalex.org/W3176072782","https://openalex.org/W3192495122","https://openalex.org/W4206498464","https://openalex.org/W4206797693","https://openalex.org/W4239396298","https://openalex.org/W4283791551","https://openalex.org/W4385245566","https://openalex.org/W6625168331","https://openalex.org/W6679434410","https://openalex.org/W6713197267","https://openalex.org/W6745410505","https://openalex.org/W6752909555","https://openalex.org/W6757817989","https://openalex.org/W6766673545","https://openalex.org/W6774569510","https://openalex.org/W6778042986","https://openalex.org/W6788033646","https://openalex.org/W6791208006"],"related_works":["https://openalex.org/W4307535225","https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W2883921205","https://openalex.org/W4313162113","https://openalex.org/W1884363728"],"abstract_inverted_index":{"Named":[0],"entity":[1],"recognition":[2],"(NER)":[3],"is":[4,73,121],"a":[5,83,95,146,155,163,214],"fundamental":[6],"task":[7,120],"for":[8,50,162,199,204],"several":[9],"important":[10],"applications":[11],"such":[12,53],"as":[13,260,262],"knowledge":[14],"base":[15],"construction":[16],"and":[17,80,107,152,218,221,246,256],"semantic":[18],"search.":[19],"So":[20],"far,":[21],"the":[22,66,100,105,112,116,138,173,200,226,236,250,269],"focus":[23],"has":[24],"been":[25],"on":[26,225],"building":[27],"machine":[28],"learning":[29],"models,":[30],"which":[31],"identify":[32],"generic":[33],"named":[34,63,168,202],"entities":[35,64,203],"(e.g.,":[36,65],"person,":[37],"date).":[38],"Such":[39],"models":[40,54,86,217,237],"can":[41,194,238],"be":[42],"used":[43],"off-the-shelf":[44],"without":[45],"requiring":[46],"ground":[47,77,196],"truth":[48,78,197],"labels":[49,161,179,198,251],"training.":[51],"However,":[52],"cannot":[55],"generalize":[56,239],"to":[57,75,89,130,158,268],"specialized":[58],"domains":[59],"that":[60,172,180,233],"have":[61],"domain-specific":[62],"legal":[67,117,139,150],"domain).":[68],"In":[69],"these":[70],"cases,":[71],"it":[72,125],"inevitable":[74],"generate":[76,159,195],"data":[79],"experiment":[81,212],"with":[82,213],"variety":[84],"of":[85,149,165,188,208,216,235],"in":[87,115],"order":[88],"achieve":[90],"good":[91],"performance.":[92],"Motivated":[93],"by":[94,253],"real":[96],"use":[97],"case":[98],"from":[99],"financial":[101],"sector,":[102],"we":[103,143,211],"discuss":[104],"approach":[106,175],"lessons":[108],"learned":[109],"when":[110],"solving":[111,137],"NER":[113,141,184,227],"problem":[114],"domain.":[118],"This":[119],"particularly":[122],"challenging":[123],"because":[124],"requires":[126],"extensive":[127],"human":[128,254],"expertise":[129],"produce":[131],"high":[132,177],"quality":[133,178],"ground-truth":[134],"labels.":[135],"For":[136],"domain":[140],"problem,":[142],"first":[144],"crawl":[145],"large":[147],"dataset":[148],"documents":[151],"then":[153],"introduce":[154],"semi-automated":[156],"process":[157],"high-quality":[160],"set":[164,215],"eleven":[166],"predefined":[167],"entities.":[169],"We":[170],"validate":[171],"proposed":[174],"achieves":[176],"outperform":[181],"popular":[182],"out-of-the-box":[183],"methods.":[185],"On":[186],"top":[187],"that,":[189],"our":[190,257,263],"method":[191],"once":[192],"followed,":[193],"pre-defined":[201],"an":[205],"unbounded":[206],"number":[207],"documents.":[209],"Next,":[210],"training":[219],"procedures":[220],"report":[222],"their":[223],"performance":[224],"task.":[228],"Our":[229],"experimental":[230],"evaluation":[231],"confirms":[232],"most":[234],"very":[240],"well,":[241],"achieving":[242],"F1-score":[243],"between":[244],"86%":[245],"98.9%.":[247],"The":[248],"dataset,":[249],"produced":[252],"annotators":[255],"semi-supervised":[258],"approach,":[259],"well":[261],"code":[264],"are":[265],"made":[266],"available":[267],"research":[270],"community.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}