{"id":"https://openalex.org/W2788885658","doi":"https://doi.org/10.1145/3178876.3186028","title":"Inferring Missing Categorical Information in Noisy and Sparse Web Markup","display_name":"Inferring Missing Categorical Information in Noisy and Sparse Web Markup","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2788885658","doi":"https://doi.org/10.1145/3178876.3186028","mag":"2788885658"},"language":"en","primary_location":{"id":"doi:10.1145/3178876.3186028","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186028","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186028&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3186028&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nicolas Tempelmeier","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicolas Tempelmeier","raw_affiliation_strings":["Leibniz Universit\u00e4t, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Universit\u00e4t, Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Elena Demidova","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elena Demidova","raw_affiliation_strings":["Leibniz Universit\u00e4t, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Universit\u00e4t, Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"last","author":{"id":null,"display_name":"Stefan Dietze","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Dietze","raw_affiliation_strings":["Leibniz Universit\u00e4t, Hannover, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Universit\u00e4t, Hannover, Germany","institution_ids":["https://openalex.org/I114112103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114112103"],"apc_list":null,"apc_paid":null,"fwci":2.415,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91278293,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1297","last_page":"1306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9991000294685364,"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":0.9976000189781189,"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/categorical-variable","display_name":"Categorical variable","score":0.7170000076293945},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.7055000066757202},{"id":"https://openalex.org/keywords/microdata","display_name":"Microdata (statistics)","score":0.5396000146865845},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.46230000257492065},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4366999864578247},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4253000020980835},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.40529999136924744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7170000076293945},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.7055000066757202},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.5396000146865845},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.3546999990940094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33869999647140503},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3178876.3186028","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186028","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186028&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.00446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.00446","pdf_url":"https://arxiv.org/pdf/1803.00446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1145/3178876.3186028","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186028","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186028&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3161986504","display_name":"AFEL - Analytics For Everyday Learning","funder_award_id":"687916","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3810325836","display_name":null,"funder_award_id":"02K15A040","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788885658.pdf","grobid_xml":"https://content.openalex.org/works/W2788885658.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2536126309","https://openalex.org/W2883403137","https://openalex.org/W2885604786"],"related_works":[],"abstract_inverted_index":{"Embedded":[0],"markup":[1,62,115],"of":[2,34,88,113,173,180],"Web":[3,36,52,54,114,127,166],"pages":[4,37],"has":[5],"seen":[6],"widespread":[7],"adoption":[8,31],"throughout":[9],"the":[10,82,109,126],"past":[11],"years":[12],"driven":[13],"by":[14,32],"standards":[15],"such":[16,23,50],"as":[17,24,51],"RDFa":[18],"and":[19,21,68,95,111,175,182],"Microdata":[20],"initiatives":[22],"schema.org,":[25],"where":[26],"recent":[27],"studies":[28],"show":[29,177],"an":[30,44],"39%":[33],"all":[35],"already":[38],"in":[39,85,128,131,165],"2016.":[40],"While":[41],"this":[42,153],"constitutes":[43,138],"important":[45],"information":[46,121,145],"source":[47],"for":[48,133,142,160],"tasks":[49],"search,":[53],"page":[55],"classification":[56],"or":[57],"knowledge":[58],"graph":[59],"augmentation,":[60],"individual":[61],"nodes":[63,78,89,98,117],"are":[64,100],"usually":[65],"sparsely":[66,149],"described":[67,150],"often":[69],"lack":[70],"essential":[71],"information.":[72],"For":[73],"instance,":[74],"from":[75,125],"26":[76],"million":[77],"describing":[79],"events":[80,174],"within":[81],"Common":[83],"Crawl":[84],"2016,":[86],"59%":[87],"provide":[90,119],"less":[91],"than":[92],"six":[93],"statements":[94],"only":[96],"257,000":[97],"(0.96%)":[99],"typed":[101],"with":[102],"more":[103],"specific":[104],"event":[105],"subtypes.":[106],"Nevertheless,":[107],"given":[108],"scale":[110],"diversity":[112],"data,":[116],"that":[118],"missing":[120,144,162],"can":[122],"be":[123],"obtained":[124],"large":[129],"quantities,":[130],"particular":[132],"categorical":[134,163],"properties.":[135],"Such":[136],"data":[137,141],"potential":[139],"training":[140],"inferring":[143,161],"to":[146],"significantly":[147,187],"augment":[148],"nodes.":[151],"In":[152],"work,":[154],"we":[155],"introduce":[156],"a":[157,178],"supervised":[158],"approach":[159],"properties":[164,172],"markup.":[167],"Our":[168],"experiments,":[169],"conducted":[170],"on":[171],"movies,":[176],"performance":[179],"79%":[181],"83%":[183],"F1":[184],"score":[185],"correspondingly,":[186],"outperforming":[188],"existing":[189],"baselines.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2018-03-06T00:00:00"}