{"id":"https://openalex.org/W4393474977","doi":"https://doi.org/10.5281/zenodo.8091584","title":"Wikidata Thematic Subgraph Selection","display_name":"Wikidata Thematic Subgraph Selection","publication_year":2023,"publication_date":"2023-06-28","ids":{"openalex":"https://openalex.org/W4393474977","doi":"https://doi.org/10.5281/zenodo.8091584"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.8091584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8091584","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.8091584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092362918","display_name":"Lucas Jarnac","orcid":"https://orcid.org/0000-0002-2819-2679"},"institutions":[{"id":"https://openalex.org/I126469861","display_name":"Orange (Poland)","ror":"https://ror.org/05dt0hn88","country_code":"PL","type":"company","lineage":["https://openalex.org/I126469861","https://openalex.org/I19370010"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Jarnac, Lucas","raw_affiliation_strings":["Orange"],"affiliations":[{"raw_affiliation_string":"Orange","institution_ids":["https://openalex.org/I126469861"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066732273","display_name":"Miguel Couceiro","orcid":"https://orcid.org/0000-0003-2316-7623"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Couceiro, Miguel","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, LORIA"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, LORIA","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088952442","display_name":"Pierre Monnin","orcid":"https://orcid.org/0000-0002-2017-8426"},"institutions":[{"id":"https://openalex.org/I126469861","display_name":"Orange (Poland)","ror":"https://ror.org/05dt0hn88","country_code":"PL","type":"company","lineage":["https://openalex.org/I126469861","https://openalex.org/I19370010"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Monnin, Pierre","raw_affiliation_strings":["Orange"],"affiliations":[{"raw_affiliation_string":"Orange","institution_ids":["https://openalex.org/I126469861"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092362918"],"corresponding_institution_ids":["https://openalex.org/I126469861"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10028","display_name":"Topic Modeling","score":0.9878000020980835,"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":0.9878000020980835,"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":0.9794999957084656,"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":0.9746999740600586,"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/thematic-map","display_name":"Thematic map","score":0.7438539862632751},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7163443565368652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5280947089195251},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3886914551258087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23344650864601135},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.23288586735725403},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1528725028038025}],"concepts":[{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.7438539862632751},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7163443565368652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5280947089195251},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3886914551258087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23344650864601135},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.23288586735725403},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1528725028038025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.8091584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8091584","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.8091584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.8091584","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2291311298","https://openalex.org/W2378021067","https://openalex.org/W2347703439","https://openalex.org/W2371027582","https://openalex.org/W2076654158","https://openalex.org/W2362328851","https://openalex.org/W2366119473","https://openalex.org/W2372311246","https://openalex.org/W2368605609"],"abstract_inverted_index":{"Wikidata":[0],"Thematic":[1],"Subgraph":[2],"Selection":[3],"These":[4],"datasets":[5,85],"have":[6],"been":[7],"designed":[8],"to":[9,14,207],"train":[10,208],"and":[11,50,178,197,209,224],"evaluate":[12],"algorithms":[13],"select":[15],"thematic":[16],"subgraphs":[17],"of":[18,28,37,40,61,69,219],"interest":[19,62],"in":[20],"a":[21,35,42,146,169,189],"large":[22],"knowledge":[23],"graph":[24,43],"from":[25,58,72],"seed":[26,38,59,73,151,174,193],"entities":[27],"interest.":[29],"Specifically,":[30],"we":[31],"consider":[32],"Wikidata.":[33],"Given":[34],"set":[36],"QIDs":[39,60,74,89],"interest,":[41],"expansion":[44],"is":[45],"performed":[46],"following":[47],"P31,":[48],"P279,":[49],"(-)P279":[51],"edges.":[52],"Traversed":[53],"classes":[54,70],"that":[55,75],"thematically":[56],"deviates":[57],"should":[63],"be":[64],"pruned.":[65],"Datasets":[66,229],"thus":[67],"consist":[68],"reached":[71,195],"are":[76,230],"labeled":[77,199,215],"as":[78],"\"to":[79,82],"prune\"":[80],"or":[81],"keep\".":[83],"Available":[84],"Dataset":[86],"#":[87,90,93,102,111,115],"Seed":[88],"Labeled":[91],"decisions":[92,95,104,216],"Prune":[94],"Min":[96,105],"prune":[97,100],"depth":[98,101,107,110],"Max":[99,108],"Keep":[103],"keep":[106,109],"Reached":[112,116],"nodes":[113,117],"up":[114],"down":[118],"dataset1":[119,221],"455":[120],"5233":[121],"3464":[122],"1":[123,126,134,137],"4":[124,127],"1769":[125],"1507":[128],"2593609":[129],"dataset2":[130,225],"105":[131],"982":[132],"388":[133],"2":[135],"594":[136],"3":[138],"1159":[139],"1247385":[140],"Each":[141],"dataset":[142],"folder":[143],"contains":[144],"datasetX.csv:":[145],"CSV":[147,163,170,190],"file":[148,164,171,191],"containing":[149,172],"one":[150,173],"QID":[152,175],"per":[153,176],"line":[154,177],"(not":[155,181],"the":[156,160,182,186,198,214,233],"complete":[157,183],"URL,":[158,184],"just":[159,185],"QID).":[161],"This":[162],"has":[165],"no":[166],"header.":[167],"datasetX_labels.csv:":[168],"its":[179],"label":[180],"QID)":[187],"datasetX_gold_decisions.csv:":[188],"with":[192],"QIDs,":[194,196],"decision":[200],"(1:":[201],"keep,":[202],"0:":[203],"prune)":[204],"datasetX_Y_folds.pkl:":[205],"folds":[206],"test":[210],"models":[211],"based":[212],"on":[213],"dataset1-2":[217],"consists":[218],"using":[220],"for":[222,226],"training":[223],"testing.":[227],"License":[228],"available":[231],"under":[232],"CC":[234],"BY-NC":[235],"license.":[236]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
