{"id":"https://openalex.org/W4402810185","doi":"https://doi.org/10.3233/ssw240004","title":"Leveraging Semantic Model and LLM for Bootstrapping a Legal Entity Extraction: An Industrial Use Case","display_name":"Leveraging Semantic Model and LLM for Bootstrapping a Legal Entity Extraction: An Industrial Use Case","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402810185","doi":"https://doi.org/10.3233/ssw240004"},"language":"en","primary_location":{"id":"doi:10.3233/ssw240004","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240004","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","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/ssw240004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064693527","display_name":"Julien Breton","orcid":"https://orcid.org/0000-0001-8285-0399"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Julien Breton","raw_affiliation_strings":["Berger-Levrault, Toulouse, France","Informatics Research Institute of Toulouse (IRIT), Toulouse, France","IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"Berger-Levrault, Toulouse, France","institution_ids":[]},{"raw_affiliation_string":"Informatics Research Institute of Toulouse (IRIT), Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422"]},{"raw_affiliation_string":"IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049342040","display_name":"Mokhtar Boumedyen Billami","orcid":"https://orcid.org/0000-0003-4428-4298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mokhtar Boumedyen Billami","raw_affiliation_strings":["Berger-Levrault, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"Berger-Levrault, Toulouse, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085908375","display_name":"Max Chevalier","orcid":"https://orcid.org/0000-0001-5402-6255"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Max Chevalier","raw_affiliation_strings":["Informatics Research Institute of Toulouse (IRIT), Toulouse, France","IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"Informatics Research Institute of Toulouse (IRIT), Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422"]},{"raw_affiliation_string":"IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084471742","display_name":"C\u00e1ssia Trojahn dos Santos","orcid":"https://orcid.org/0000-0003-2840-005X"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cassia Trojahn","raw_affiliation_strings":["Informatics Research Institute of Toulouse (IRIT), Toulouse, France","IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"Informatics Research Institute of Toulouse (IRIT), Toulouse, France","institution_ids":["https://openalex.org/I4210119061","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210160189","https://openalex.org/I4210152422"]},{"raw_affiliation_string":"IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064693527"],"corresponding_institution_ids":["https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"],"apc_list":null,"apc_paid":null,"fwci":28.2372,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9959214,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9944999814033508,"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":0.9944999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9607999920845032,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9264000058174133,"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/pipeline","display_name":"Pipeline (software)","score":0.6744287610054016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6592879891395569},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5586282014846802},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5097188353538513},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46334347128868103},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4285215735435486},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3777536153793335},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24465054273605347},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12366703152656555},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.11302244663238525}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6744287610054016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592879891395569},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5586282014846802},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5097188353538513},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46334347128868103},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4285215735435486},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3777536153793335},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24465054273605347},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12366703152656555},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.11302244663238525},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/ssw240004","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240004","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-04719513v1","is_oa":true,"landing_page_url":"https://ut3-toulouseinp.hal.science/hal-04719513","pdf_url":"https://ut3-toulouseinp.hal.science/hal-04719513v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Semantics 2024 - 20th International Conference on Semantic Systems, Sep 2024, Amterdam, Netherlands. &#x27E8;10.3233/ssw240004&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"doi:10.3233/ssw240004","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ssw240004","pdf_url":null,"source":{"id":"https://openalex.org/S4210172742","display_name":"Studies on the semantic web","issn_l":"2215-0870","issn":["2215-0870"],"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":"ebook platform"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies on the Semantic Web","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W156620619","https://openalex.org/W2616249226","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W2997844990","https://openalex.org/W1598221548","https://openalex.org/W2081850291","https://openalex.org/W1963695443"],"abstract_inverted_index":{"Compliance":[0],"with":[1],"legal":[2,20,50,89,137],"documents":[3,21],"related":[4],"to":[5,12,33,66,103],"industrial":[6,114],"maintenance":[7],"is":[8,74],"the":[9,35,47,88,105,108,113,118,134,141],"company\u2019s":[10],"obligation":[11],"oversee,":[13],"maintain,":[14],"and":[15,37,97],"repair":[16],"its":[17],"equipments.":[18],"As":[19],"endlessly":[22],"evolve,":[23],"companies":[24],"are":[25],"in":[26,44,101],"favour":[27],"of":[28,49,64,107,136,143],"automatically":[29],"processing":[30],"these":[31],"texts":[32],"facilitate":[34],"analysis":[36],"compliance.":[38],"The":[39],"automatic":[40],"process":[41],"involves":[42],"first,":[43],"this":[45,70,84],"pipeline,":[46],"extraction":[48,91,135],"entities.":[51],"However,":[52],"state-of-the-art,":[53],"like":[54],"BERT":[55],"approaches,":[56],"have":[57],"so":[58],"far":[59],"required":[60],"a":[61,75,98],"large":[62],"amount":[63],"data":[65],"be":[67],"effective.":[68],"Creating":[69],"training":[71],"dataset":[72],"however":[73],"time-consuming":[76],"task":[77],"requiring":[78],"input":[79],"from":[80],"domain":[81,109],"experts.":[82,110,144],"In":[83],"paper,":[85],"we":[86,123],"bootstrap":[87],"entity":[90],"by":[92,116],"levering":[93],"Large":[94],"Language":[95],"Models":[96],"semantic":[99],"model":[100],"order":[102],"reduce":[104],"involvement":[106,142],"We":[111],"develop":[112],"perspective":[115],"detailing":[117],"technical":[119],"implementation":[120],"choices.":[121],"Consequently,":[122],"present":[124],"our":[125],"roadmap":[126],"for":[127,133],"an":[128],"end-to-end":[129],"pipeline":[130],"designed":[131],"expressly":[132],"rules":[138],"while":[139],"limiting":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
