{"id":"https://openalex.org/W4405247702","doi":"https://doi.org/10.3390/bdcc8120185","title":"From Fact Drafts to Operational Systems: Semantic Search in Legal Decisions Using Fact Drafts","display_name":"From Fact Drafts to Operational Systems: Semantic Search in Legal Decisions Using Fact Drafts","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4405247702","doi":"https://doi.org/10.3390/bdcc8120185"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc8120185","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8120185","pdf_url":"https://www.mdpi.com/2504-2289/8/12/185/pdf?version=1733820132","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/8/12/185/pdf?version=1733820132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060181276","display_name":"Gergely M\u00e1rk Cs\u00e1nyi","orcid":"https://orcid.org/0000-0001-8475-5969"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gergely M\u00e1rk Cs\u00e1nyi","raw_affiliation_strings":["MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-8475-5969","affiliations":[{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091479125","display_name":"Dorina Lakatos","orcid":"https://orcid.org/0009-0007-4644-9486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dorina Lakatos","raw_affiliation_strings":["MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0009-0007-4644-9486","affiliations":[{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020960256","display_name":"Istv\u00e1n \u00dcveges","orcid":"https://orcid.org/0000-0001-5897-9379"},"institutions":[{"id":"https://openalex.org/I4210137611","display_name":"Centre for Social Sciences","ror":"https://ror.org/0492k9x16","country_code":"HU","type":"facility","lineage":["https://openalex.org/I4210137611","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Istv\u00e1n \u00dcveges","raw_affiliation_strings":["HUN-REN Centre for Social Sciences, Toth Kalman Street 4, 1097 Budapest, Hungary","MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-5897-9379","affiliations":[{"raw_affiliation_string":"HUN-REN Centre for Social Sciences, Toth Kalman Street 4, 1097 Budapest, Hungary","institution_ids":["https://openalex.org/I4210137611"]},{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023736136","display_name":"Andrea Megyeri","orcid":"https://orcid.org/0000-0001-7689-9989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Megyeri","raw_affiliation_strings":["Wolters Kluwer Hungary Kft., Budafoki Street 187-189, 1117 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-7689-9989","affiliations":[{"raw_affiliation_string":"Wolters Kluwer Hungary Kft., Budafoki Street 187-189, 1117 Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078175373","display_name":"J\u00e1nos P\u00e1l Vad\u00e1sz","orcid":"https://orcid.org/0000-0003-3848-6096"},"institutions":[{"id":"https://openalex.org/I1331168281","display_name":"Ludovika University of Public Service","ror":"https://ror.org/040yeqy86","country_code":"HU","type":"education","lineage":["https://openalex.org/I1331168281"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"J\u00e1nos P\u00e1l Vad\u00e1sz","raw_affiliation_strings":["Institute of the Information Society, National University of Public Service, Ludovika Square 2, 1083 Budapest, Hungary","MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-3848-6096","affiliations":[{"raw_affiliation_string":"Institute of the Information Society, National University of Public Service, Ludovika Square 2, 1083 Budapest, Hungary","institution_ids":["https://openalex.org/I1331168281"]},{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074217475","display_name":"D\u00e1niel Nagy","orcid":"https://orcid.org/0000-0003-0467-1410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D\u00e1niel Nagy","raw_affiliation_strings":["MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0003-0467-1410","affiliations":[{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026432196","display_name":"Ren\u00e1t\u00f3 V\u00e1gi","orcid":"https://orcid.org/0000-0002-2019-5349"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Ren\u00e1t\u00f3 V\u00e1gi","raw_affiliation_strings":["Doctoral School of Law, E\u00f6tv\u00f6s Lor\u00e1nd University, Egyetem Square 1-3, 1053 Budapest, Hungary","MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","Wolters Kluwer Hungary Kft., Budafoki Street 187-189, 1117 Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-2019-5349","affiliations":[{"raw_affiliation_string":"Doctoral School of Law, E\u00f6tv\u00f6s Lor\u00e1nd University, Egyetem Square 1-3, 1053 Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]},{"raw_affiliation_string":"MONTANA Knowledge Management Ltd., H\u00e1rsalja Street 32, 1029 Budapest, Hungary","institution_ids":[]},{"raw_affiliation_string":"Wolters Kluwer Hungary Kft., Budafoki Street 187-189, 1117 Budapest, Hungary","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5060181276"],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.1257,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90965148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"8","issue":"12","first_page":"185","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9958999752998352,"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":0.9800999760627747,"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":0.7948595285415649},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6246690154075623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5440641045570374},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5125138759613037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5114044547080994},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5113177299499512},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46715205907821655},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45926961302757263},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4589340388774872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948595285415649},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6246690154075623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5440641045570374},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5125138759613037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114044547080994},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5113177299499512},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46715205907821655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45926961302757263},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4589340388774872},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/bdcc8120185","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8120185","pdf_url":"https://www.mdpi.com/2504-2289/8/12/185/pdf?version=1733820132","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:35307","is_oa":true,"landing_page_url":null,"pdf_url":"http://publicatio.bibl.u-szeged.hu/35307/1/BDCC-08-00185.pdf","source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:doaj.org/article:caadd56247c146b9b1f424225da985ee","is_oa":true,"landing_page_url":"https://doaj.org/article/caadd56247c146b9b1f424225da985ee","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 8, Iss 12, p 185 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc8120185","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8120185","pdf_url":"https://www.mdpi.com/2504-2289/8/12/185/pdf?version=1733820132","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405247702.pdf","grobid_xml":"https://content.openalex.org/works/W4405247702.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1542990879","https://openalex.org/W2145343266","https://openalex.org/W2147277317","https://openalex.org/W2231690509","https://openalex.org/W2493916176","https://openalex.org/W2496235729","https://openalex.org/W2949255687","https://openalex.org/W2970641574","https://openalex.org/W2986154550","https://openalex.org/W3034707327","https://openalex.org/W3035390927","https://openalex.org/W3103187652","https://openalex.org/W3135361293","https://openalex.org/W3156716744","https://openalex.org/W3180395890","https://openalex.org/W3213215942","https://openalex.org/W4210308685","https://openalex.org/W4212947051","https://openalex.org/W4225249966","https://openalex.org/W4287704453","https://openalex.org/W4294170691","https://openalex.org/W4302008968","https://openalex.org/W4324193559","https://openalex.org/W4375869328","https://openalex.org/W4380369889","https://openalex.org/W4385245566","https://openalex.org/W4385800295","https://openalex.org/W4386576685","https://openalex.org/W4390682142","https://openalex.org/W4392054049","https://openalex.org/W4393161188","https://openalex.org/W4402670856","https://openalex.org/W6682691769","https://openalex.org/W6723821839","https://openalex.org/W6739901393","https://openalex.org/W6781533629","https://openalex.org/W6811103846","https://openalex.org/W6845038366"],"related_works":["https://openalex.org/W4376653378","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349","https://openalex.org/W4385239468","https://openalex.org/W4200476258","https://openalex.org/W2022470916","https://openalex.org/W3201962287","https://openalex.org/W3002840018"],"abstract_inverted_index":{"This":[0],"research":[1],"paper":[2],"presents":[3],"findings":[4],"from":[5,206],"an":[6,32,258],"investigation":[7],"in":[8,226],"the":[9,15,29,58,75,119,146,173,194,199,207,215,228,235,245],"semantic":[10,34,260],"similarity":[11,35],"search":[12,36,261],"task":[13],"within":[14,91],"legal":[16,47,83,252,266],"domain,":[17],"using":[18,45],"a":[19,115,232,264],"corpus":[20],"of":[21,88,97,128,175,193,231,240,244],"1172":[22],"Hungarian":[23],"court":[24],"decisions.":[25],"The":[26,101,169,242],"study":[27,76,102],"establishes":[28],"groundwork":[30],"for":[31,60,82,198,263],"operational":[33,259],"system":[37,262],"designed":[38],"to":[39,221,257],"identify":[40],"cases":[41,90],"with":[42,161,185],"comparable":[43],"facts":[44],"preliminary":[46],"fact":[48,80],"drafts.":[49],"Evaluating":[50],"such":[51],"systems":[52],"often":[53],"poses":[54],"significant":[55,238],"challenges,":[56],"given":[57],"need":[59],"thorough":[61],"document":[62,233],"checks,":[63],"which":[64],"can":[65],"be":[66],"costly":[67],"and":[68,94,137,156,223,249],"limit":[69],"evaluation":[70],"reusability.":[71],"To":[72,144],"address":[73],"this,":[74],"employs":[77],"manually":[78],"created":[79],"drafts":[81],"cases,":[84],"enabling":[85],"reliable":[86],"ranking":[87],"original":[89],"retrieved":[92],"documents":[93],"quantitative":[95],"comparison":[96],"various":[98],"vectorization":[99],"methods.":[100],"compares":[103],"twelve":[104],"different":[105],"text":[106,236],"embedding":[107,167],"solutions":[108],"(the":[109],"most":[110],"recent":[111],"became":[112],"available":[113],"just":[114],"few":[116],"weeks":[117],"before":[118],"manuscript":[120],"was":[121,247],"written)":[122],"identifying":[123],"Cohere\u2019s":[124],"embed-multilingual-v3.0,":[125],"Beijing":[126],"Academy":[127],"Artificial":[129],"Intelligence\u2019s":[130],"bge-m3,":[131],"Jina":[132],"AI\u2019s":[133],"jina-embeddings-v3,":[134],"OpenAI\u2019s":[135],"text-embedding-3-large,":[136],"Microsoft\u2019s":[138],"multilingual-e5-large":[139],"models":[140,208,225],"as":[141],"top":[142],"performers.":[143],"overcome":[145],"transformer-based":[147],"models\u2019":[148],"context":[149,195,213],"window":[150,196,214],"limitation,":[151],"we":[152],"investigated":[153],"chunking,":[154],"striding,":[155],"last":[157,162],"chunk":[158,163],"scaling":[159,164],"techniques,":[160],"significantly":[165],"improving":[166],"quality.":[168],"results":[170],"suggest":[171],"that":[172,205],"effectiveness":[174],"striding":[176,184],"varies":[177],"based":[178],"on":[179],"token":[180,211],"count.":[181],"Notably,":[182],"employing":[183],"16":[186],"tokens":[187],"yielded":[188],"optimal":[189],"results,":[190],"representing":[191],"3.125%":[192],"size":[197],"best-performing":[200],"models.":[201],"Results":[202],"also":[203],"suggested":[204],"having":[209],"8192":[210],"long":[212],"bge-m3":[216],"model":[217],"is":[218],"superior":[219],"compared":[220],"jina-embeddings-v3":[222],"text-embedding-3-large":[224],"capturing":[227],"relevant":[229],"parts":[230],"if":[234],"contains":[237],"amount":[239],"noise.":[241],"validity":[243],"approach":[246],"evaluated":[248],"confirmed":[250],"by":[251],"experts.":[253],"These":[254],"insights":[255],"led":[256],"prominent":[265],"content":[267],"provider.":[268]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2024-12-11T00:00:00"}