{"id":"https://openalex.org/W4416988411","doi":"https://doi.org/10.3233/faia251605","title":"Comparison of Embedding Methods for Retrieval Under Noisy Institutional Labels","display_name":"Comparison of Embedding Methods for Retrieval Under Noisy Institutional Labels","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416988411","doi":"https://doi.org/10.3233/faia251605"},"language":null,"primary_location":{"id":"doi:10.3233/faia251605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251605","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251605","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000074756","display_name":"Tereza Novotn\u00e1","orcid":"https://orcid.org/0000-0002-1426-4547"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Tereza Novotn\u00e1","raw_affiliation_strings":["Faculty of Law, Masaryk University, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Faculty of Law, Masaryk University, Brno, Czechia","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086310558","display_name":"Jakub Hara\u0161ta","orcid":"https://orcid.org/0000-0002-5722-0325"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jakub Hara\u0161ta","raw_affiliation_strings":["Faculty of Law, Masaryk University, Brno, Czechia"],"affiliations":[{"raw_affiliation_string":"Faculty of Law, Masaryk University, Brno, Czechia","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000074756"],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.783866,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.7279999852180481,"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":0.7279999852180481,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.03359999880194664,"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"}},{"id":"https://openalex.org/T14013","display_name":"Legal Language and Interpretation","score":0.021299999207258224,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"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/embedding","display_name":"Embedding","score":0.7343000173568726},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6208999752998352},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5640000104904175},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4490000009536743},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.44020000100135803},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4140999913215637},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7343000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318999767303467},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4490000009536743},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251605","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251605","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251605","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Retrieving":[0],"relevant":[1],"case":[2],"law":[3],"remains":[4],"a":[5,19,26,37],"time-consuming":[6],"task.":[7],"We":[8,35],"compare":[9],"two":[10],"embedding":[11],"models":[12],"for":[13],"Czech":[14],"Constitutional":[15],"Court":[16],"decisions:":[17],"(i)":[18],"large":[20],"general-purpose":[21],"OpenAI":[22,66],"embedder":[23,67],"and":[24,53,69,78],"(ii)":[25],"domain-specific":[27],"BERT":[28,74],"trained":[29],"from":[30],"scratch":[31],"on":[32],"\u223c34,000":[33],"decisions.":[34],"introduce":[36],"noise-aware":[38],"evaluation":[39,84],"using":[40],"IDF-weighted":[41],"keyword":[42],"overlap":[43],"as":[44],"graded":[45],"relevance,":[46],"dual":[47],"thresholds":[48],"(0.20,":[49],"0.28),":[50],"paired-bootstrap":[51],"significance,":[52],"nDCG":[54,59],"diagnostics.":[55],"Despite":[56],"conservative":[57],"absolute":[58],"due":[60],"to":[61],"noisy":[62],"institutional":[63],"labels,":[64],"the":[65,72],"consistently":[68],"significantly":[70],"outperforms":[71],"domain":[73],"across":[75],"all":[76],"ranks":[77],"thresholds.":[79],"Our":[80],"framework":[81],"enables":[82],"robust":[83],"under":[85],"imperfect":[86],"gold":[87],"standards":[88],"typical":[89],"of":[90],"legacy":[91],"judicial":[92],"databases.":[93]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-04T00:00:00"}