{"id":"https://openalex.org/W2891515342","doi":"https://doi.org/10.4149/cai_2018_4_969","title":"Annotating Web Tables with the Crowd","display_name":"Annotating Web Tables with the Crowd","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891515342","doi":"https://doi.org/10.4149/cai_2018_4_969","mag":"2891515342"},"language":"en","primary_location":{"id":"doi:10.4149/cai_2018_4_969","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_4_969","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4149/cai_2018_4_969","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100387096","display_name":"Ning Wang","orcid":"https://orcid.org/0000-0001-8903-8790"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Wang","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, 100044 Beijing"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, 100044 Beijing","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006435045","display_name":"Huaxi Liu","orcid":"https://orcid.org/0000-0002-8583-3698"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaxi Liu","raw_affiliation_strings":["School of Computer and Information Technology, Beijing Jiaotong University, 100044 Beijing"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Technology, Beijing Jiaotong University, 100044 Beijing","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100387096"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.2118,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60203429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"37","issue":"4","first_page":"969","last_page":"991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8289852142333984},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7572649717330933},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5849694013595581},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.5606759786605835},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5447921752929688},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5130466222763062},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5007929801940918},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4885583817958832},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.4598676860332489},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.45778360962867737},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.444713830947876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43727993965148926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41102129220962524},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3941497206687927},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.239854097366333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289852142333984},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7572649717330933},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5849694013595581},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.5606759786605835},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5447921752929688},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5130466222763062},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5007929801940918},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4885583817958832},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.4598676860332489},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.45778360962867737},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.444713830947876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43727993965148926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41102129220962524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3941497206687927},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.239854097366333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4149/cai_2018_4_969","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_4_969","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4149/cai_2018_4_969","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_4_969","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114","https://openalex.org/W2405355225"],"abstract_inverted_index":{"The":[0,150],"Web":[1],"contains":[2],"a":[3,52,139,148],"large":[4],"amount":[5],"of":[6,10,64,82,100,138,152],"structured":[7],"tables,":[8,173],"most":[9,111],"which":[11,134],"lacks":[12],"header":[13],"rows.":[14],"Algorithmic":[15],"approaches":[16],"have":[17],"been":[18],"proposed":[19,95],"to":[20,41,60,75,96,103,108],"recover":[21],"semantics":[22],"for":[23,114,147,171,186],"web":[24,65,172],"tables":[25],"by":[26],"annotating":[27],"column":[28],"labels":[29],"and":[30,45,117,168,174,178,184],"identifying":[31],"subject":[32],"columns.":[33],"However,":[34],"state-of-the-art":[35],"technology":[36],"is":[37,94,127,182],"not":[38],"yet":[39],"able":[40],"provide":[42],"satisfactory":[43],"accuracy":[44,167],"recall.":[46],"In":[47,68,106],"this":[48,69],"paper,":[49],"we":[50],"present":[51],"hybrid":[53],"machine-crowdsourcing":[54],"framework":[55,162],"that":[56,160],"leverages":[57],"human":[58,77,115],"intelligence":[59],"improve":[61,165],"the":[62,98,104,110,119,136,144],"performance":[63],"table":[66],"annotation.":[67],"framework,":[70],"machine-based":[71],"algorithms":[72],"are":[73],"used":[74],"prompt":[76],"workers":[78,116],"with":[79],"candidate":[80],"lists":[81],"concepts,":[83],"while":[84],"an":[85,124],"improved":[86],"K-means":[87],"algorithm":[88],"based":[89,130],"on":[90,131,156],"novel":[91],"integrative":[92],"distance":[93],"minimize":[97],"number":[99],"tuples":[101],"posed":[102],"crowd.":[105],"order":[107],"recommend":[109],"related":[112],"tasks":[113],"determine":[118],"final":[120,145],"answers":[121],"more":[122],"accurately,":[123],"evaluation":[125,180],"mechanism":[126,181],"also":[128],"implemented":[129],"Answer":[132],"Credibility":[133],"measures":[135],"probability":[137],"worker's":[140],"intuitive":[141],"answer":[142,146,179,188],"being":[143],"task.":[149],"results":[151],"extensive":[153],"experiments":[154],"conducted":[155],"real-world":[157],"datasets":[158],"show":[159],"our":[161,175],"can":[163],"significantly":[164],"annotation":[166],"time":[169],"efficiency":[170],"task":[176],"reduction":[177],"effective":[183],"efficient":[185],"improving":[187],"quality.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
