{"id":"https://openalex.org/W7213639095","doi":"https://doi.org/10.5281/zenodo.22834004","title":"Arabic Entity Linking Surface-Form Coverage: benchmark, anchor dictionary and surface-form pool","display_name":"Arabic Entity Linking Surface-Form Coverage: benchmark, anchor dictionary and surface-form pool","publication_year":2026,"publication_date":"2026-09-18","ids":{"openalex":"https://openalex.org/W7213639095","doi":"https://doi.org/10.5281/zenodo.22834004"},"language":"ar","primary_location":{"id":"doi:10.5281/zenodo.22834004","doi":"https://doi.org/10.5281/zenodo.22834004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22834004","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22834004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152250681","display_name":"Anes Abdelouahab Mahammedi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405255857","display_name":"Evolutionary Engineering & Distributed Information Systems Laboratory","ror":"https://ror.org/03gewjm80","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514","https://openalex.org/I4405255857"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Mahammedi, Anes Abdelouahab","raw_affiliation_strings":["EEDIS Laboratory, University of Naama, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Naama, Algeria","institution_ids":["https://openalex.org/I4405255857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030824332","display_name":"Abdelghani Bouziane","orcid":"https://orcid.org/0000-0002-8583-3858","observed_orcids":["https://orcid.org/0000-0002-8583-3858"]},"institutions":[{"id":"https://openalex.org/I4405255857","display_name":"Evolutionary Engineering & Distributed Information Systems Laboratory","ror":"https://ror.org/03gewjm80","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514","https://openalex.org/I4405255857"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Bouziane, Abdelghani","raw_affiliation_strings":["EEDIS Laboratory, University of Naama, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Naama, Algeria","institution_ids":["https://openalex.org/I4405255857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045776797","display_name":"Yasser Yahiaoui","orcid":"https://orcid.org/0009-0006-4435-4734","observed_orcids":["https://orcid.org/0009-0006-4435-4734"]},"institutions":[{"id":"https://openalex.org/I4405255857","display_name":"Evolutionary Engineering & Distributed Information Systems Laboratory","ror":"https://ror.org/03gewjm80","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514","https://openalex.org/I4405255857"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Yahiaoui, Yasser","raw_affiliation_strings":["EEDIS Laboratory, University of Naama, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Naama, Algeria","institution_ids":["https://openalex.org/I4405255857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031007388","display_name":"Djelloul Bouchiha","orcid":"https://orcid.org/0000-0001-7314-4329","observed_orcids":["https://orcid.org/0000-0001-7314-4329"]},"institutions":[{"id":"https://openalex.org/I4405255857","display_name":"Evolutionary Engineering & Distributed Information Systems Laboratory","ror":"https://ror.org/03gewjm80","country_code":"DZ","type":"education","lineage":["https://openalex.org/I4210125514","https://openalex.org/I4405255857"]}],"countries":["DZ"],"is_corresponding":false,"raw_author_name":"Bouchiha, Djelloul","raw_affiliation_strings":["EEDIS Laboratory, University of Naama, Algeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEDIS Laboratory, University of Naama, Algeria","institution_ids":["https://openalex.org/I4405255857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405255857"],"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":0.7851999998092651,"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":0.7851999998092651,"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":0.2013999968767166,"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/T11719","display_name":"Data Quality and Management","score":0.005499999970197678,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/arabic-wikipedia","display_name":"Arabic Wikipedia","score":0.640999972820282},{"id":"https://openalex.org/keywords/wikidata","display_name":"Wikidata","score":0.9789999723434448},{"id":"https://openalex.org/keywords/string-matching","display_name":"string matching","score":0.6480000019073486},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.6959999799728394},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861999869346619},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7660999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5648000240325928},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44859999418258667},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26669999957084656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.22834004","doi":"https://doi.org/10.5281/zenodo.22834004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22834004","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22834005","doi":"https://doi.org/10.5281/zenodo.22834005","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22834005","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22964063","doi":"https://doi.org/10.5281/zenodo.22964063","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22964063","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22834004","doi":"https://doi.org/10.5281/zenodo.22834004","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22834004","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,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221027452","https://openalex.org/W7220928434","https://openalex.org/W6950534346","https://openalex.org/W2250865411","https://openalex.org/W2752855602","https://openalex.org/W7099230276","https://openalex.org/W7099971265","https://openalex.org/W6941179441","https://openalex.org/W2571687252","https://openalex.org/W6903925491"],"abstract_inverted_index":{"Resources":[0],"accompanying":[1],"the":[2,68,75,92,97,105,112,117],"study":[3],"How":[4],"Far":[5],"Can":[6],"String":[7],"Matching":[8],"Take":[9],"Arabic":[10,19,24,30,59],"Entity":[11],"Linking?":[12],"Layered":[13],"Surface-Form":[14],"Coverage":[15],"in":[16,115],"Wikidata":[17,54,70],"and":[18,56,63,71,74,79,87,111],"Wikipedia.":[20],"Contents:":[21],"a":[22,34,46],"200,000-mention":[23],"entity-linking":[25],"evaluation":[26],"set":[27],"built":[28],"from":[29],"Wikipedia":[31,60,72],"anchors":[32],"with":[33,50],"held-out":[35],"split;":[36],"an":[37],"anchor":[38,64],"dictionary":[39],"of":[40,67],"over":[41],"two":[42],"million":[43],"surface-form/entity":[44],"pairs;":[45],"combined":[47],"surface-form":[48],"pool":[49],"per-row":[51],"provenance":[52],"covering":[53],"labels":[55],"aliases,":[57],"ParaNames,":[58],"titles,":[61],"redirects":[62],"text;":[65],"snapshots":[66],"underlying":[69],"tables;":[73],"dialect-label":[76],"filtering":[77],"data":[78,118],"pipeline.":[80],"See":[81],"README.md":[82],"for":[83],"file":[84],"schemas,":[85],"licensing":[86],"known":[88],"limitations.":[89],"PROVENANCE.json":[90],"records":[91],"snapshot":[93,113],"dates":[94,114],"without":[95],"which":[96],"figures":[98],"cannot":[99],"be":[100],"reproduced.":[101],"Version":[102],"1.1.0":[103],"adds":[104],"analysis":[106],"code":[107],"(code.zip,":[108],"MIT":[109],"licence)":[110],"PROVENANCE.json;":[116],"files":[119],"are":[120],"unchanged.":[121]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-09-20T00:00:00"}
