{"id":"https://openalex.org/W7162626489","doi":"https://doi.org/10.5281/zenodo.20430480","title":"Smarter Extraction of Scholarly Metadata using Knowledge Graphs and Language Models","display_name":"Smarter Extraction of Scholarly Metadata using Knowledge Graphs and Language Models","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162626489","doi":"https://doi.org/10.5281/zenodo.20430480"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.20430480","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20430480","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":false,"raw_source_name":null,"raw_type":"article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.20430480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075061875","display_name":"Muhammad Asif Suryani","orcid":"https://orcid.org/0000-0003-1669-5524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suryani, Muhammad Asif","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1669-5524","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084801856","display_name":"Brigitte Mathiak","orcid":"https://orcid.org/0000-0003-1793-9615"},"institutions":[{"id":"https://openalex.org/I4210101898","display_name":"GESIS - Leibniz Institute for the Social Sciences","ror":"https://ror.org/018afyw53","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210101898"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mathiak, Brigitte","raw_affiliation_strings":["GESIS Leibniz-Institut fur Sozialwissenschaften in Koln"],"raw_orcid":"https://orcid.org/0000-0003-1793-9615","affiliations":[{"raw_affiliation_string":"GESIS Leibniz-Institut fur Sozialwissenschaften in Koln","institution_ids":["https://openalex.org/I4210101898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014573765","display_name":"Florian Reitz","orcid":"https://orcid.org/0000-0001-6114-3388"},"institutions":[{"id":"https://openalex.org/I2799853480","display_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","ror":"https://ror.org/00k4h2615","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2799853480","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reitz, Florian","raw_affiliation_strings":["Schloss Dagstuhl Leibniz-Zentrum f\u00fcr Informatik GmbH: Wadern, Saarland, DE"],"raw_orcid":"https://orcid.org/0000-0001-6114-3388","affiliations":[{"raw_affiliation_string":"Schloss Dagstuhl Leibniz-Zentrum f\u00fcr Informatik GmbH: Wadern, Saarland, DE","institution_ids":["https://openalex.org/I2799853480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124829746","display_name":"Florian J\u00e4ckel","orcid":null},"institutions":[{"id":"https://openalex.org/I2799853480","display_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","ror":"https://ror.org/00k4h2615","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2799853480","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00e4ckel, Florian","raw_affiliation_strings":["Schloss Dagstuhl \u2013 Leibniz Center for Informatics: Wadern, DE"],"raw_orcid":"https://orcid.org/0000-0001-7307-1051","affiliations":[{"raw_affiliation_string":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics: Wadern, DE","institution_ids":["https://openalex.org/I2799853480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005533034","display_name":"Ansgar Scherp","orcid":"https://orcid.org/0000-0002-2653-9245"},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]},{"id":"https://openalex.org/I4210163522","display_name":"Technische Hochschule Ulm","ror":"https://ror.org/05e5kd476","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210163522"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Scherp, Ansgar","raw_affiliation_strings":["Ulm University: Ulm, DE"],"raw_orcid":"https://orcid.org/0000-0002-2653-9245","affiliations":[{"raw_affiliation_string":"Ulm University: Ulm, DE","institution_ids":["https://openalex.org/I196349391","https://openalex.org/I4210163522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67526415,"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/T11937","display_name":"Research Data Management Practices","score":0.47110000252723694,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11937","display_name":"Research Data Management Practices","score":0.47110000252723694,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.07370000332593918,"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":0.061799999326467514,"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/metadata","display_name":"Metadata","score":0.948199987411499},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5584999918937683},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4481000006198883},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42890000343322754},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.40779998898506165},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.3986000120639801},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.39719998836517334},{"id":"https://openalex.org/keywords/geospatial-metadata","display_name":"Geospatial metadata","score":0.37940001487731934}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.948199987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036999702453613},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5896999835968018},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48190000653266907},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.37940001487731934},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.37549999356269836},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.20430480","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20430480","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":"article"}],"best_oa_location":{"id":"doi:10.5281/zenodo.20430480","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.20430480","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":false,"raw_source_name":null,"raw_type":"article"},"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":{"Scholarly":[0],"metadata":[1,20,47,63,149],"is":[2],"an":[3],"essential":[4],"element":[5],"in":[6,29,112,127],"the":[7,26,30,128],"scholarly":[8,50,133],"ecosystem,":[9],"empowering":[10],"discovery,":[11],"interoperability,":[12],"and":[13,15,22,32,55,82,122,136,161],"provenance":[14],"its":[16],"efficacy":[17],"relies":[18],"on":[19,157],"quality":[21],"coverage.":[23],"However,":[24],"with":[25,154],"substantial":[27],"increase":[28],"number":[31],"diversity":[33],"of":[34,93,130],"research":[35,114,131,152],"artifacts":[36,60],"over":[37],"time,":[38],"it":[39],"has":[40],"become":[41],"a":[42,90,155],"cumbersome":[43],"task":[44],"to":[45,88,101,142],"harvest":[46],"features":[48,150],"for":[49],"publications,":[51],"datasets,":[52],"source":[53],"code,":[54],"machine":[56],"learning":[57],"models.":[58],"These":[59],"generate":[61],"heterogeneous":[62],"features,":[64],"which":[65],"are":[66,83],"distributed":[67],"across":[68,95],"various":[69],"repositories.":[70],"In":[71],"addition,":[72],"large":[73,158],"language":[74,159],"models":[75,160],"(LLMs)":[76],"have":[77],"emerged":[78],"as":[79],"powerful":[80],"tools":[81],"now":[84],"being":[85],"extensively":[86],"adopted":[87],"facilitate":[89],"wide":[91],"range":[92],"tasks":[94],"domains,":[96],"ranging":[97],"from":[98,151],"information":[99,134],"extraction":[100],"knowledge":[102,162],"graphs.":[103,163],"Nevertheless,":[104],"numerous":[105],"open":[106,137],"questions":[107],"persist":[108],"regarding":[109],"their":[110,118],"adoption":[111],"diversified":[113],"disciplines,":[115],"especially":[116],"concerning":[117],"accuracy,":[119],"robustness,":[120],"biases,":[121],"societal":[123],"impact":[124],"when":[125],"applied":[126],"context":[129],"metadata,":[132],"extraction,":[135],"science.":[138],"This":[139],"workshop":[140],"aims":[141],"cover":[143],"these":[144],"exciting":[145],"aspects":[146],"centered":[147],"around":[148],"artifacts,":[153],"focus":[156]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-05-29T00:00:00"}