{"id":"https://openalex.org/W4393724695","doi":"https://doi.org/10.5281/zenodo.7429037","title":"Dataset for Named Entity Recognition and Entity Linking from Greek Wikipedia Events","display_name":"Dataset for Named Entity Recognition and Entity Linking from Greek Wikipedia Events","publication_year":2022,"publication_date":"2022-12-12","ids":{"openalex":"https://openalex.org/W4393724695","doi":"https://doi.org/10.5281/zenodo.7429037"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:7429037","is_oa":true,"landing_page_url":"https://zenodo.org/record/7429037","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/7429037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039707613","display_name":"Katerina Papantoniou","orcid":"https://orcid.org/0000-0003-1731-2951"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Papantoniou, Katerina","raw_affiliation_strings":["Foundation for Research and Technology (Forth)"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology (Forth)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073440687","display_name":"Vasilis Efthymiou","orcid":"https://orcid.org/0000-0002-0683-030X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Efthymiou, Vasilis","raw_affiliation_strings":["Foundation for Research and Technology (Forth))"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology (Forth))","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004081767","display_name":"Dimitris Plexousakis","orcid":"https://orcid.org/0000-0002-0863-8266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Plexousakis, Dimitris","raw_affiliation_strings":["Foundation for Research and Technology (Forth)"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology (Forth)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039707613"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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":0.9969000220298767,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7312630414962769},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.7154985070228577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5930774807929993},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4678569436073303},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4583131968975067},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4245501458644867},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31367945671081543},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06487426161766052},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.062073081731796265},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.04913097620010376}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7312630414962769},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.7154985070228577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5930774807929993},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4678569436073303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4583131968975067},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4245501458644867},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31367945671081543},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06487426161766052},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.062073081731796265},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.04913097620010376},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:7429037","is_oa":true,"landing_page_url":"https://zenodo.org/record/7429037","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.7429037","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7429037","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":"pmh:oai:zenodo.org:7429037","is_oa":true,"landing_page_url":"https://zenodo.org/record/7429037","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W4255258373","https://openalex.org/W2032007337","https://openalex.org/W3000685722","https://openalex.org/W1884363728","https://openalex.org/W4253099099","https://openalex.org/W4386977977","https://openalex.org/W4200491110","https://openalex.org/W4390279576"],"abstract_inverted_index":{"An":[0],"automated":[1],"benchmark":[2],"dataset":[3,35,60,78,98],"for":[4,200,209],"(Named":[5,10],"Entity":[6,11],"Recognition)":[7],"NER":[8],"and":[9,48,69,93,151,202,205,211],"Linking)":[12],"NEL":[13],"tools,":[14],"based":[15],"on":[16],"Greek":[17],"Wikipedia":[18,31],"events":[19,63],"pages.":[20],"Note:":[21],"This":[22,191],"data":[23,25],"includes":[24],"from":[26,196],"the":[27,39,59,197,206],"following":[28],"sources:
":[29],"-":[30],"el.wikipedia.org":[32],"Description":[33],"The":[34,55,77],"is":[36,141],"provided":[37],"in":[38,50],"form":[40],"of":[41,53,58,95],"three":[42],"JSON-formatted":[43],"subsets":[44],"i.e.,":[45],"train,":[46],"validation":[47],"test":[49],"an":[51],"analogy":[52],"70-20-10.":[54],"current":[56],"version":[57],"contains":[61,79],"18,617":[62,131],"annotated":[64],"with":[65],"40,798":[66,134],"entity":[67,84],"mentions":[68],"36,189":[70,135],"links":[71],"to":[72,82],"elWikipedia":[73],"(and":[74],"wikidata":[75],"ids).":[76],"annotations":[80],"belonging":[81],"8":[83],"types:":[85],"person,":[86],"organization,":[87],"location,":[88],"gpe,":[89],"event,":[90],"facility,":[91],"product":[92],"work":[94,192],"art.":[96],"Overall":[97],"statistics":[99],"Docs":[100],"Tokens":[101],"Sentences":[102],"Surface":[103],"Mentions":[104],"Valid":[105],"Links":[106,108],"Red":[107],"Train":[109],"13,031":[110],"332,077":[111],"16,927":[112],"28,593":[113],"25,365":[114],"3,228":[115],"Validation":[116],"3,722":[117],"94,746":[118],"4,844":[119],"8,168":[120],"7,240":[121],"928":[122],"Test":[123],"1,862":[124],"47,450":[125],"2,427":[126],"4,037":[127],"3,584":[128],"453":[129],"Total":[130],"474,361":[132],"24,200":[133],"4,609":[136],"Example":[137],"A":[138],"record":[139],"example":[140],"given":[142],"below.":[143],"{":[144],"\"json_file\":":[145],"\"February":[146],"2012_39_0":[147],"events\",
":[148],"\"text\":":[149],"\"Sudan":[150],"South":[152],"Sudan":[153],"sign":[154],"non-aggression":[155],"pact.\",
":[156],"\"ground_truth_mentions\":":[157],"[
":[158,178],"{\"start\":":[159,167],"0,":[160],"\"end\":":[161,169],"4,":[162],"\"surface_mention\":":[163,171],"\"Sudan\",":[164],"\"mention_type\":":[165,174],"\"GPE\"},
":[166],"10,":[168],"20,":[170],"\"South":[172],"Sudan\",":[173],"\"GPE\"}
":[175],"],
":[176],"\"ground_truth_links\":":[177],"{\"enwiki\":":[179,182],"\"Sudan\",\"wikidata\":":[180],"\"Q1049\"},
":[181],"\"South_Sudan\",":[183],"\"wikidata\":":[184],"\"Q958\"}
":[185],"]
":[186],"}":[187],"Code":[188],"https://gitlab.isl.ics.forth.gr/debatelab/elwiki_events_benchmark":[189],"Acknowledgments":[190],"has":[193],"received":[194],"funding":[195],"Hellenic":[198],"Foundation":[199],"Research":[201,210],"Innovation":[203],"(HFRI)":[204],"General":[207],"Secretariat":[208],"Technology":[212],"(GSRT),":[213],"under":[214],"grant":[215],"agreement":[216],"No":[217],"4195.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}