{"id":"https://openalex.org/W4416034041","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.671","title":"Schema Generation for Large Knowledge Graphs Using Large Language Models","display_name":"Schema Generation for Large Knowledge Graphs Using Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034041","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.671"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.671","pdf_url":"https://aclanthology.org/2025.findings-emnlp.671.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.671.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004868214","display_name":"Bohui Zhang","orcid":"https://orcid.org/0000-0001-5430-1624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohui Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461968","display_name":"Yuan He","orcid":"https://orcid.org/0000-0002-4486-1262"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020931166","display_name":"Lydia Pintscher","orcid":"https://orcid.org/0000-0002-3939-2115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lydia Pintscher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019540386","display_name":"Albert Mero\u00f1o-Pe\u00f1uela","orcid":"https://orcid.org/0000-0003-4646-5842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albert Mero\u00f1o-Pe\u00f1uela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046030036","display_name":"Elena Simperl","orcid":"https://orcid.org/0000-0003-1722-947X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Simperl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93679341,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12561","last_page":"12580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6906999945640564,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6906999945640564,"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/T10028","display_name":"Topic Modeling","score":0.0625,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.0272000003606081,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/knowledge-graph","display_name":"Knowledge graph","score":0.49470001459121704},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.46000000834465027},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3776000142097473},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.32330000400543213},{"id":"https://openalex.org/keywords/conceptual-graph","display_name":"Conceptual graph","score":0.32260000705718994},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3156000077724457},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.304500013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7114999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46219998598098755},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C234837","wikidata":"https://www.wikidata.org/wiki/Q1420493","display_name":"Conceptual graph","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C100481476","wikidata":"https://www.wikidata.org/wiki/Q4055684","display_name":"First-order logic","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.671","pdf_url":"https://aclanthology.org/2025.findings-emnlp.671.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.671","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.671","pdf_url":"https://aclanthology.org/2025.findings-emnlp.671.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322923","display_name":"Siemens","ror":"https://ror.org/059mq0909"},{"id":"https://openalex.org/F4320323383","display_name":"Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/02kkvpp62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034041.pdf","grobid_xml":"https://content.openalex.org/works/W4416034041.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Schemas":[0],"play":[1],"a":[2,109],"vital":[3],"role":[4],"in":[5,12,39,82,90],"ensuring":[6],"data":[7],"quality":[8],"and":[9,16,28,60,72],"supporting":[10],"usability":[11],"the":[13,31,51,96,116],"Semantic":[14],"Web":[15],"natural":[17],"language":[18,36],"processing.Traditionally,":[19],"their":[20],"creation":[21],"demands":[22],"substantial":[23],"involvement":[24],"from":[25,75],"knowledge":[26,76],"engineers":[27],"domain":[29],"experts.Leveraging":[30],"impressive":[32],"capabilities":[33],"of":[34,118],"large":[35,104],"models":[37],"(LLMs)":[38],"tasks":[40],"like":[41],"ontology":[42],"engineering,":[43],"we":[44,54],"explore":[45],"schema":[46,101],"generation":[47,102],"using":[48],"LLMs.To":[49],"bridge":[50],"resource":[52],"gap,":[53],"introduce":[55],"two":[56],"datasets:":[57],"YAGO":[58],"Schema":[59],"Wikidata":[61],"EntitySchema,":[62],"along":[63],"with":[64],"novel":[65],"evaluation":[66],"metrics.The":[67],"LLMbased":[68],"pipelines":[69],"utilize":[70],"local":[71],"global":[73],"information":[74],"graphs":[77],"(KGs)":[78],"to":[79],"generate":[80],"schemas":[81],"Shape":[83],"Expressions":[84],"(ShEx).Experiments":[85],"demonstrate":[86],"LLMs'":[87],"strong":[88],"potential":[89],"producing":[91],"high-quality":[92],"ShEx":[93],"schemas,":[94],"paving":[95],"way":[97],"for":[98,103,112],"scalable,":[99],"automated":[100],"KGs.Furthermore,":[105],"our":[106],"benchmark":[107],"introduces":[108],"new":[110],"challenge":[111],"structured":[113],"generation,":[114],"pushing":[115],"limits":[117],"LLMs":[119],"on":[120],"syntactically":[121],"rich":[122],"formalisms.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}