{"id":"https://openalex.org/W4297206544","doi":"https://doi.org/10.48550/arxiv.2204.06347","title":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","display_name":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","publication_year":2022,"publication_date":"2022-04-13","ids":{"openalex":"https://openalex.org/W4297206544","doi":"https://doi.org/10.48550/arxiv.2204.06347"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2204.06347","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06347","pdf_url":"https://arxiv.org/pdf/2204.06347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.06347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087218475","display_name":"Xuwu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xuwu","raw_affiliation_strings":["School of Computer Science , Fudan University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102413215","display_name":"Junfeng Tian","orcid":"https://orcid.org/0000-0001-6638-6418","observed_orcids":["https://orcid.org/0000-0001-6638-6418","https://orcid.org/0000-0002-7068-8002"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian, Junfeng","raw_affiliation_strings":["Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113110337","display_name":"Min Gui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gui, Min","raw_affiliation_strings":["Shopee , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shopee , Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065529268","display_name":"Zhixu Li","orcid":"https://orcid.org/0000-0003-2355-288X","observed_orcids":["https://orcid.org/0000-0003-2355-288X"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhixu","raw_affiliation_strings":["School of Computer Science , Fudan University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431149","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-8007-2503","observed_orcids":["https://orcid.org/0000-0001-8007-2503"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rui","raw_affiliation_strings":["Vipshop (China) Co. , Ltd. , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vipshop (China) Co. , Ltd. , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878","observed_orcids":["https://orcid.org/0000-0003-4959-8878"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Ming","raw_affiliation_strings":["Alibaba Group , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030104017","display_name":"Lihan Chen","orcid":"https://orcid.org/0000-0002-0337-4177","observed_orcids":["https://orcid.org/0000-0002-0337-4177","https://orcid.org/0000-0003-0807-9684","https://orcid.org/0009-0001-0606-0317"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Lihan","raw_affiliation_strings":["School of Computer Science , Fudan University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , Fudan University , China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090455375","display_name":"Yanghua Xiao","orcid":"https://orcid.org/0000-0001-8403-9591","observed_orcids":["https://orcid.org/0000-0001-8403-9591"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Yanghua","raw_affiliation_strings":["Fudan-Aishu Cognitive Intelligence Joint Research Center , China","School of Computer Science , Fudan University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan-Aishu Cognitive Intelligence Joint Research Center , China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science , Fudan University , China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0006000000284984708,"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":0.0,"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/multimodal-entity-linking","display_name":"multimodal entity linking","score":1.0},{"id":"https://openalex.org/keywords/annotated-data","display_name":"annotated dataset","score":0.8019999861717224},{"id":"https://openalex.org/keywords/wikinews","display_name":"Wikinews","score":0.7419999837875366},{"id":"https://openalex.org/keywords/wikipedia-knowledge-base","display_name":"Wikipedia knowledge base","score":0.9520000219345093},{"id":"https://openalex.org/keywords/entity-types","display_name":"entity types","score":0.9940000176429749},{"id":"https://openalex.org/keywords/manual-annotation","display_name":"manual annotation","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154991269111633},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.7963926792144775},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6828484535217285},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6307799816131592},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6169087886810303},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6009846925735474},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5755984783172607},{"id":"https://openalex.org/C2777096784","wikidata":"https://www.wikidata.org/wiki/Q3826351","display_name":"Referent","level":2,"score":0.5509726405143738},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5042484998703003},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5007238388061523},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49172666668891907},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47372332215309143},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41448843479156494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3884832262992859},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35448306798934937},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06969380378723145},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2204.06347","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06347","pdf_url":"https://arxiv.org/pdf/2204.06347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.06347","doi":"https://doi.org/10.48550/arxiv.2204.06347","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.06347","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.06347","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.06347","pdf_url":"https://arxiv.org/pdf/2204.06347","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G296198563","display_name":null,"funder_award_id":"2021SHZDZX0103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3277427600","display_name":"\u5f00\u653e\u591a\u6a21\u6001\u73af\u5883\u4e0b\u52a8\u6001\u77e5\u8bc6\u56fe\u8c31\u8865\u5168\u4e0e\u66f4\u65b0\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3205420591","https://openalex.org/W3210283180","https://openalex.org/W4393160894","https://openalex.org/W6947700793","https://openalex.org/W4409365198","https://openalex.org/W4412826005","https://openalex.org/W7157256494","https://openalex.org/W4408345722","https://openalex.org/W7172288642","https://openalex.org/W7118008403"],"abstract_inverted_index":{"Multimodal":[0],"Entity":[1],"Linking":[2],"(MEL)":[3],"which":[4,88,125],"aims":[5],"at":[6,169],"linking":[7],"mentions":[8],"with":[9,79,118],"multimodal":[10,28],"contexts":[11],"to":[12,36,61,102,144],"the":[13,38,62,92,104,107,127,146,156],"referent":[14],"entities":[15],"from":[16,86],"a":[17,74,112],"knowledge":[18,94],"base":[19],"(e.g.,":[20],"Wikipedia),":[21],"is":[22,100],"an":[23],"essential":[24],"task":[25],"for":[26],"many":[27],"applications.":[29],"Although":[30],"much":[31],"attention":[32],"has":[33],"been":[34],"paid":[35],"MEL,":[37,154],"shortcomings":[39],"of":[40,66,106,114,130,148,153],"existing":[41,135],"MEL":[42,77,116,136],"datasets":[43],"including":[44],"limited":[45],"contextual":[46,81],"topics":[47,82],"and":[48,54,64,83,120,164],"entity":[49,84],"types,":[50],"simplified":[51],"mention":[52],"ambiguity,":[53],"restricted":[55],"availability,":[56],"have":[57],"caused":[58],"great":[59],"obstacles":[60],"research":[63,158],"application":[65],"MEL.":[67],"In":[68],"this":[69,160],"paper,":[70],"we":[71],"present":[72],"WikiDiverse,":[73,111],"high-quality":[75],"human-annotated":[76],"dataset":[78,163],"diversified":[80],"types":[85],"Wikinews,":[87],"uses":[89],"Wikipedia":[90],"as":[91],"corresponding":[93],"base.":[95],"A":[96],"well-tailored":[97],"annotation":[98],"procedure":[99],"adopted":[101],"ensure":[103],"quality":[105],"dataset.":[108],"Based":[109],"on":[110,159],"sequence":[113],"well-designed":[115],"models":[117,137,166],"intra-modality":[119],"inter-modality":[121],"attentions":[122],"are":[123,142,167],"implemented,":[124],"utilize":[126],"visual":[128],"information":[129],"images":[131],"more":[132],"adequately":[133],"than":[134],"do.":[138],"Extensive":[139],"experimental":[140],"analyses":[141],"conducted":[143],"investigate":[145],"contributions":[147],"different":[149],"modalities":[150],"in":[151],"terms":[152],"facilitating":[155],"future":[157],"task.":[161],"The":[162],"baseline":[165],"available":[168],"https://github.com/wangxw5/wikiDiverse.":[170]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2022-09-27T00:00:00"}
