{"id":"https://openalex.org/W4415958573","doi":"https://doi.org/10.1145/3731443.3771342","title":"Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties","display_name":"Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4415958573","doi":"https://doi.org/10.1145/3731443.3771342"},"language":"en","primary_location":{"id":"doi:10.1145/3731443.3771342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771342","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3731443.3771342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009898821","display_name":"C\u00e9lian Ringwald","orcid":"https://orcid.org/0000-0002-7302-9037"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"C\u00e9lian Ringwald","raw_affiliation_strings":["Wimmics, Universit\u00e9 C\u00f4te d\u2019Azur, Inria, CNRS, I3S, Sophia Antipolis, France","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)"],"affiliations":[{"raw_affiliation_string":"Wimmics, Universit\u00e9 C\u00f4te d\u2019Azur, Inria, CNRS, I3S, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044946197","display_name":"Fabien Gandon","orcid":"https://orcid.org/0000-0003-0543-1232"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210106479","display_name":"Laboratoire d'Informatique, Signaux et Syst\u00e8mes de Sophia Antipolis","ror":"https://ror.org/01215r597","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I201841394","https://openalex.org/I4210106479","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4390039363","display_name":"Infection et inflammation","ror":"https://ror.org/021sh3243","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4390039363"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabien Gandon","raw_affiliation_strings":["Wimmics, INRIA, Sophia Antipolis, France","Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S\r\nCS 40121\r\n06903 Sophia Antipolis Cedex - France)","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)"],"affiliations":[{"raw_affiliation_string":"Wimmics, INRIA, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S\r\nCS 40121\r\n06903 Sophia Antipolis Cedex - France)","institution_ids":["https://openalex.org/I4210106479","https://openalex.org/I4390039363"]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018628204","display_name":"Catherine Faron Zucker","orcid":"https://orcid.org/0000-0001-5959-5561"},"institutions":[{"id":"https://openalex.org/I201841394","display_name":"Universit\u00e9 C\u00f4te d'Azur","ror":"https://ror.org/019tgvf94","country_code":"FR","type":"education","lineage":["https://openalex.org/I201841394"]},{"id":"https://openalex.org/I4210106479","display_name":"Laboratoire d'Informatique, Signaux et Syst\u00e8mes de Sophia Antipolis","ror":"https://ror.org/01215r597","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I201841394","https://openalex.org/I4210106479","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210117840","display_name":"Institut de Biologie Valrose","ror":"https://ror.org/03bnma344","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I201841394","https://openalex.org/I4210096427","https://openalex.org/I4210117840"]},{"id":"https://openalex.org/I4210150884","display_name":"Fondation Sophia Antipolis","ror":"https://ror.org/05nkcfv27","country_code":"FR","type":"other","lineage":["https://openalex.org/I4210150884"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Catherine Faron","raw_affiliation_strings":["Wimmics, Universit\u00e9 C\u00f4te d'Azur, Sophia Antipolis, France","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","I3S - Laboratoire d'Informatique, Signaux, et Syst\u00e8mes de Sophia Antipolis (2000, route des Lucioles - Les Algorithmes - b\u00e2t. Euclide B 06900 Sophia Antipolis - France)","UniCA - Universit\u00e9 C\u00f4te d'Azur (Parc Valrose, 28, avenue Valrose 06108 Nice Cedex 2 - France)"],"affiliations":[{"raw_affiliation_string":"Wimmics, Universit\u00e9 C\u00f4te d'Azur, Sophia Antipolis, France","institution_ids":["https://openalex.org/I4210150884","https://openalex.org/I201841394"]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","institution_ids":[]},{"raw_affiliation_string":"I3S - Laboratoire d'Informatique, Signaux, et Syst\u00e8mes de Sophia Antipolis (2000, route des Lucioles - Les Algorithmes - b\u00e2t. Euclide B 06900 Sophia Antipolis - France)","institution_ids":["https://openalex.org/I4210106479"]},{"raw_affiliation_string":"UniCA - Universit\u00e9 C\u00f4te d'Azur (Parc Valrose, 28, avenue Valrose 06108 Nice Cedex 2 - France)","institution_ids":["https://openalex.org/I4210117840","https://openalex.org/I201841394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032122043","display_name":"Franck Michel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210106479","display_name":"Laboratoire d'Informatique, Signaux et Syst\u00e8mes de Sophia Antipolis","ror":"https://ror.org/01215r597","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I201841394","https://openalex.org/I4210106479","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4390039363","display_name":"Infection et inflammation","ror":"https://ror.org/021sh3243","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I4390039363"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Franck Michel","raw_affiliation_strings":["I3S, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, Sophia Antipolis, France, France","Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S\r\nCS 40121\r\n06903 Sophia Antipolis Cedex - France)","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)"],"affiliations":[{"raw_affiliation_string":"I3S, Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, Sophia Antipolis, France, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S\r\nCS 40121\r\n06903 Sophia Antipolis Cedex - France)","institution_ids":["https://openalex.org/I4210106479","https://openalex.org/I4390039363"]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036765049","display_name":"Hanna Abi Akl","orcid":"https://orcid.org/0000-0001-9829-7401"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Hanna Abi Akl","raw_affiliation_strings":["Universit\u00e9 C\u00f4te d\u2019Azur, Inria, CNRS, I3S / Data ScienceTech Institute, Sophia Antipolis, France","WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","DSTI Labs - Data ScienceTech Institute (Les Templiers\r\n950 Route des Colles\r\nSophia-Antipolis\r\n06410 Biot - France)"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 C\u00f4te d\u2019Azur, Inria, CNRS, I3S / Data ScienceTech Institute, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics (2004 route des lucioles\r\n06902 Sophia Antipolis - France)","institution_ids":[]},{"raw_affiliation_string":"DSTI Labs - Data ScienceTech Institute (Les Templiers\r\n950 Route des Colles\r\nSophia-Antipolis\r\n06410 Biot - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009898821"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16853132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3970000147819519,"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":0.3970000147819519,"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":0.19859999418258667,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0925000011920929,"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/bottleneck","display_name":"Bottleneck","score":0.7365999817848206},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.6618000268936157},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.589900016784668},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5519000291824341},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5479999780654907},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5148000121116638},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5134999752044678},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5101000070571899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109999895095825},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7365999817848206},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.6618000268936157},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5148000121116638},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44190001487731934},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.42640000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33570000529289246},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25279998779296875},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3731443.3771342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771342","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.03407","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.03407","pdf_url":"https://arxiv.org/pdf/2511.03407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05285428v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05285428","pdf_url":"https://hal.science/hal-05285428/document","source":{"id":"https://openalex.org/S4406922454","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":"KCAP 2025 - The Thirteenth International Conference on Knowledge Capture, ACM, Dec 2025, Dayton, OH, USA,, United States","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2511.03407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.03407","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5281/zenodo.15917324","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917324","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"},{"id":"doi:10.5281/zenodo.15917325","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15917325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.1145/3731443.3771342","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731443.3771342","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Knowledge Capture Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4622970671","display_name":null,"funder_award_id":"ANR-23-IACL-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5348246107","display_name":null,"funder_award_id":"ANR-15-IDEX-0","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5348977864","display_name":null,"funder_award_id":"ANR-15-IDEX-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7166692799","display_name":null,"funder_award_id":"ANR-15-I","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7996427589","display_name":null,"funder_award_id":"ANR-15_IDEX-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8747369397","display_name":null,"funder_award_id":"NR-15-IDEX-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8800819381","display_name":null,"funder_award_id":"-15-IDEX-01","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4410356599","https://openalex.org/W4392619039","https://openalex.org/W4402670893","https://openalex.org/W3214342214","https://openalex.org/W4409347900","https://openalex.org/W4287854681","https://openalex.org/W4389524085","https://openalex.org/W2963351448","https://openalex.org/W4388144143","https://openalex.org/W4410877225","https://openalex.org/W4385574332","https://openalex.org/W2952179106","https://openalex.org/W2759211898"],"related_works":[],"abstract_inverted_index":{"Small":[0],"language":[1],"models":[2],"(SLMs)":[3],"have":[4],"shown":[5],"promises":[6],"for":[7,35,123,131],"relation":[8],"extraction":[9],"(RE)":[10],"when":[11],"extracting":[12],"RDF":[13,38],"triples":[14],"guided":[15],"by":[16],"SHACL":[17],"shapes":[18],"focused":[19],"on":[20],"common":[21],"Datatype":[22,31],"Properties.":[23],"This":[24],"paper":[25],"investigates":[26],"how":[27],"SLMs":[28,126],"handle":[29],"both":[30],"and":[32,69,116,127],"Object":[33],"Properties":[34],"a":[36,91,103],"complete":[37],"graph":[39],"extraction.":[40],"We":[41,74],"show":[42,75],"that":[43,76],"the":[44,77,95],"key":[45],"bottleneck":[46],"is":[47,88],"related":[48],"to":[49,80,89],"long-tail":[50],"distribution":[51],"of":[52,97,99],"rare":[53],"properties.":[54],"To":[55,106],"solve":[56],"this":[57],"issue,":[58],"we":[59,109],"evaluate":[60],"several":[61],"strategies:":[62],"stratified":[63],"sampling,":[64],"weighted":[65],"loss,":[66],"dataset":[67],"scaling,":[68],"template-based":[70],"synthetic":[71],"data":[72],"augmentation.":[73],"best":[78],"strategy":[79],"perform":[81],"equally":[82],"well":[83],"over":[84],"unbalanced":[85],"target":[86],"properties":[87],"build":[90],"training":[92,124],"set":[93],"where":[94],"number":[96],"occurrences":[98],"each":[100],"property":[101],"exceeds":[102],"given":[104],"threshold.":[105],"enable":[107],"reproducibility,":[108],"publicly":[110],"released":[111],"our":[112],"datasets,":[113],"experimental":[114],"results":[115],"code.":[117],"Our":[118],"findings":[119],"offer":[120],"practical":[121],"guidance":[122],"shape-aware":[125],"highlight":[128],"promising":[129],"directions":[130],"future":[132],"work":[133],"in":[134],"semantic":[135],"RE.":[136]},"counts_by_year":[],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}