{"id":"https://openalex.org/W2987330325","doi":"https://doi.org/10.1007/978-3-030-33220-4_7","title":"Using Weak Supervision to Identify Long-Tail Entities for Knowledge Base Completion","display_name":"Using Weak Supervision to Identify Long-Tail Entities for Knowledge Base Completion","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2987330325","doi":"https://doi.org/10.1007/978-3-030-33220-4_7","mag":"2987330325"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-33220-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-33220-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-33220-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-33220-4_7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028142689","display_name":"Yaser Oulabi","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yaser Oulabi","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6 26, 68159, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6 26, 68159, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, B6 26, 68159, Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, B6 26, 68159, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8807880878448486},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.7797355651855469},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6322770118713379},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5257751941680908},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5208300352096558},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5066948533058167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4856390058994293},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47489848732948303},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.46584638953208923},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.45121338963508606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4446302354335785},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41034409403800964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4095385670661926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38200703263282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8807880878448486},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.7797355651855469},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6322770118713379},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5257751941680908},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5208300352096558},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5066948533058167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4856390058994293},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47489848732948303},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.46584638953208923},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.45121338963508606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446302354335785},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41034409403800964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4095385670661926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38200703263282776},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-33220-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-33220-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-33220-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:52759","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-33220-4_7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-33220-4_7","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-33220-4_7.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2987330325.pdf","grobid_xml":"https://content.openalex.org/works/W2987330325.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1509595041","https://openalex.org/W1552847225","https://openalex.org/W1742677423","https://openalex.org/W2016753842","https://openalex.org/W2080133951","https://openalex.org/W2107598941","https://openalex.org/W2122865749","https://openalex.org/W2140190241","https://openalex.org/W2140602286","https://openalex.org/W2148524305","https://openalex.org/W2404161646","https://openalex.org/W2586196357","https://openalex.org/W2604190938","https://openalex.org/W2754180233","https://openalex.org/W2769041395","https://openalex.org/W2903440991","https://openalex.org/W2911424454","https://openalex.org/W2926124940","https://openalex.org/W2946524278","https://openalex.org/W2959716049","https://openalex.org/W2962982640","https://openalex.org/W3089010864"],"related_works":["https://openalex.org/W822806878","https://openalex.org/W2549465623","https://openalex.org/W4211238987","https://openalex.org/W2612411726","https://openalex.org/W4294432004","https://openalex.org/W969889303","https://openalex.org/W2038154115","https://openalex.org/W3187460820","https://openalex.org/W2296310460","https://openalex.org/W3158276483"],"abstract_inverted_index":{"Data":[0],"from":[1,67],"relational":[2,68],"web":[3],"tables":[4,70],"can":[5,37],"be":[6],"used":[7],"to":[8,60,133,147,177],"augment":[9],"cross-domain":[10],"knowledge":[11,32,98],"bases":[12,99],"like":[13],"DBpedia,":[14],"Wikidata,":[15],"or":[16,45],"the":[17,31,81,110,114,157],"Google":[18],"Knowledge":[19],"Graph":[20],"with":[21],"descriptions":[22,63],"of":[23,30,64,83,116,138,144,152,184],"entities":[24,36,66],"that":[25,47,129,170,179],"are":[26],"not":[27],"yet":[28],"part":[29],"base.":[33],"Such":[34],"long-tail":[35,65,117],"include":[38],"for":[39,113],"instance":[40],"small":[41,136],"villages,":[42],"niche":[43],"songs,":[44],"athletes":[46],"play":[48],"in":[49,80],"lower-level":[50],"leagues.":[51],"In":[52,104],"previous":[53],"work,":[54,106],"we":[55,107],"have":[56],"presented":[57],"an":[58],"approach":[59,128,167],"successfully":[61],"assemble":[62],"HTML":[69],"using":[71,121],"supervised":[72],"matching":[73,141],"methods":[74,178],"and":[75,85,168],"manually":[76,185],"labeled":[77,186],"training":[78,91],"data":[79,92],"form":[82],"positive":[84],"negative":[86],"entity":[87,118,153,187],"matches.":[88,188],"Manually":[89],"labeling":[90,111],"is":[93],"a":[94,126,135,149],"laborious":[95],"task":[96,115],"given":[97],"covering":[100],"many":[101],"different":[102],"classes.":[103],"this":[105,164],"investigate":[108],"reducing":[109,156],"effort":[112,160],"extraction":[119],"by":[120],"weak":[122,165],"supervision.":[123],"We":[124,162],"present":[125],"bootstrapping":[127],"requires":[130],"domain":[131],"experts":[132],"provide":[134],"set":[137,151],"simple,":[139],"class-specific":[140],"rules,":[142],"instead":[143],"requiring":[145],"them":[146],"label":[148],"large":[150,182],"matches,":[154],"thereby":[155],"human":[158],"supervision":[159,166],"considerably.":[161],"evaluate":[163],"find":[169],"it":[171],"performs":[172],"only":[173],"slightly":[174],"worse":[175],"compared":[176],"rely":[180],"on":[181],"sets":[183]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
