{"id":"https://openalex.org/W2067035576","doi":"https://doi.org/10.1145/1367497.1367632","title":"Towards a global schema for web entities","display_name":"Towards a global schema for web entities","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2067035576","doi":"https://doi.org/10.1145/1367497.1367632","mag":"2067035576"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084502605","display_name":"Conglei Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conglei Yao","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032241080","display_name":"Yongjian Yu","orcid":"https://orcid.org/0000-0001-8998-2677"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Yu","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027858196","display_name":"Sicong Shou","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicong Shou","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021280609","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0001-7085-2768"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84308198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"999","last_page":"1008"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9914000034332275,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.737816333770752},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5921217799186707},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44045987725257874},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33516639471054077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737816333770752},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5921217799186707},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44045987725257874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33516639471054077}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1367497.1367632","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2008.org/papers/pdf/p999-yaoA.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.623.7494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.623.7494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sewm.pku.edu.cn/TianwangLiterature/2008/2008-WWW-Towards a Global Schema for Web Entities.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":26,"referenced_works":["https://openalex.org/W1495559779","https://openalex.org/W1534024124","https://openalex.org/W1971318281","https://openalex.org/W1973483159","https://openalex.org/W1990117407","https://openalex.org/W2015551056","https://openalex.org/W2027780984","https://openalex.org/W2032675573","https://openalex.org/W2042389627","https://openalex.org/W2070412788","https://openalex.org/W2102667697","https://openalex.org/W2108267498","https://openalex.org/W2108350934","https://openalex.org/W2108489852","https://openalex.org/W2110686900","https://openalex.org/W2115461474","https://openalex.org/W2127855221","https://openalex.org/W2136451095","https://openalex.org/W2139135093","https://openalex.org/W2143309843","https://openalex.org/W2147858536","https://openalex.org/W2150365753","https://openalex.org/W2157060173","https://openalex.org/W2172549414","https://openalex.org/W3004612262","https://openalex.org/W3086391940"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Popular":[0],"entities":[1,80,127],"often":[2,45,59],"have":[3],"thousands":[4],"of":[5,81,117,128,195],"instances":[6,103,138,149],"on":[7,15,35,49,87,157,187,199],"the":[8,16,39,50,53,78,92,158,176,181,188],"Web.":[9],"In":[10],"this":[11,110,134],"paper,":[12],"we":[13,112],"focus":[14],"case":[17],"where":[18],"they":[19],"are":[20],"presented":[21],"in":[22,100],"table-like":[23],"format,":[24],"namely":[25],"appearing":[26],"with":[27],"their":[28,88],"attribute":[29,62,74,94,122,153,178,202],"names.":[30],"It":[31],"is":[32,67,96,141,172,217],"observed":[33],"that,":[34],"one":[36,129],"hand,":[37],"for":[38,52,76,124,180,204],"same":[40,54],"entity,":[41],"different":[42,47,56,61],"web":[43,57,79,89,101,106,126,147,164,208],"pages":[44,58],"incorporate":[46],"attributes;":[48],"other,":[51],"attribute,":[55],"use":[60],"names":[63],"(labels).":[64],"Therefore,":[65],"it":[66],"imaginably":[68],"difficult":[69],"to":[70,144,150,174],"produce":[71],"a":[72,82,114,120,166],"global":[73,93,121,177,201],"schema":[75,95,123,169,179],"all":[77,125],"given":[83],"entity":[84,102,131,148,160,183],"type":[85],"based":[86,156],"instances,":[90,161],"although":[91],"usually":[97],"highly":[98],"desired":[99],"integration":[104],"and":[105,162,197,206,220],"object":[107],"extraction.":[108],"To":[109],"end,":[111],"propose":[113],"novel":[115],"framework":[116,216],"automatically":[118],"learning":[119],"specific":[130],"type.":[132,184],"Under":[133],"framework,":[135],"an":[136],"iterative":[137],"extraction":[139],"procedure":[140],"first":[142],"employed":[143],"extract":[145],"sufficient":[146],"discover":[151],"enough":[152],"labels.":[154],"Next,":[155],"labels,":[159],"related":[163],"pages,":[165],"maximum":[167],"entropy-based":[168],"discovery":[170],"approach":[171],"adopted":[173],"learn":[175],"target":[182],"Experimental":[185],"results":[186,212],"Chinese":[189],"Web":[190],"achieve":[191],"weighted":[192],"average":[193],"Fscores":[194],"0.7122":[196],"0.7123":[198],"two":[200],"schemas":[203],"person-type":[205],"movie-type":[207],"entities,":[209],"respectively.":[210],"These":[211],"show":[213],"that":[214],"our":[215],"general,":[218],"efficient":[219],"effective.":[221]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}