{"id":"https://openalex.org/W2169463693","doi":"https://doi.org/10.1145/775152.775178","title":"SemTag and seeker","display_name":"SemTag and seeker","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2169463693","doi":"https://doi.org/10.1145/775152.775178","mag":"2169463693"},"language":"en","primary_location":{"id":"doi:10.1145/775152.775178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web  - WWW '03","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/A5074660713","display_name":"Stephen Dill","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stephen Dill","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111991767","display_name":"John A. Tomlin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John A. Tomlin","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076089598","display_name":"Jason Y. Zien","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Y. Zien","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011288864","display_name":"Nadav Eiron","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nadav Eiron","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053094139","display_name":"David Gibson","orcid":"https://orcid.org/0000-0002-7612-0530"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Gibson","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006397816","display_name":"Daniel Gruhl","orcid":"https://orcid.org/0009-0006-9124-6752"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Gruhl","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053619893","display_name":"R. Guha","orcid":"https://orcid.org/0000-0002-5499-5491"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Guha","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077736581","display_name":"Anant Jhingran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anant Jhingran","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052200294","display_name":"Tapas Kanungo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tapas Kanungo","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104023644","display_name":"Sridhar Rajagopalan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sridhar Rajagopalan","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068021191","display_name":"Andrew Tomkins","orcid":"https://orcid.org/0000-0002-1611-9255"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Tomkins","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5074660713"],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":63.047,"has_fulltext":false,"cited_by_count":457,"citation_normalized_percentile":{"value":0.99943532,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9998000264167786,"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/T11719","display_name":"Data Quality and Management","score":0.9991999864578247,"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":0.9987999796867371,"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":0.8805946707725525},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7405428290367126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7004979848861694},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.6052687168121338},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.5677615404129028},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.5215244889259338},{"id":"https://openalex.org/keywords/semantic-analytics","display_name":"Semantic analytics","score":0.5053752064704895},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48827552795410156},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4690285921096802},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44048547744750977},{"id":"https://openalex.org/keywords/semantic-grid","display_name":"Semantic grid","score":0.4365345537662506},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41172653436660767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37156832218170166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805946707725525},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7405428290367126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7004979848861694},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.6052687168121338},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.5677615404129028},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.5215244889259338},{"id":"https://openalex.org/C148792806","wikidata":"https://www.wikidata.org/wiki/Q7449046","display_name":"Semantic analytics","level":4,"score":0.5053752064704895},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48827552795410156},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4690285921096802},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44048547744750977},{"id":"https://openalex.org/C103692084","wikidata":"https://www.wikidata.org/wiki/Q1765824","display_name":"Semantic grid","level":3,"score":0.4365345537662506},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41172653436660767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37156832218170166},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/775152.775178","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twelfth international conference on World Wide Web  - WWW '03","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W51686446","https://openalex.org/W93195387","https://openalex.org/W168525779","https://openalex.org/W192304934","https://openalex.org/W192438917","https://openalex.org/W1514962553","https://openalex.org/W1533023826","https://openalex.org/W1553019137","https://openalex.org/W1557256174","https://openalex.org/W1564124598","https://openalex.org/W1577793635","https://openalex.org/W1580236550","https://openalex.org/W1608048669","https://openalex.org/W1684311429","https://openalex.org/W1691409177","https://openalex.org/W1710641084","https://openalex.org/W1765465858","https://openalex.org/W1832601430","https://openalex.org/W1930023685","https://openalex.org/W1979566122","https://openalex.org/W2023726828","https://openalex.org/W2059275719","https://openalex.org/W2066736098","https://openalex.org/W2087060113","https://openalex.org/W2090656662","https://openalex.org/W2115470070","https://openalex.org/W2130337399","https://openalex.org/W2130610812","https://openalex.org/W2133109597","https://openalex.org/W2156877380","https://openalex.org/W2164947858","https://openalex.org/W2780912412","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2387349142","https://openalex.org/W2495387725","https://openalex.org/W4229736327","https://openalex.org/W4243025272","https://openalex.org/W2377412487","https://openalex.org/W2369014150","https://openalex.org/W146038348","https://openalex.org/W1692244837","https://openalex.org/W2032956642","https://openalex.org/W2265570313"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"Seeker,":[3],"a":[4,30,52,87],"platform":[5,17],"for":[6],"large-scale":[7,97],"text":[8],"analytics,":[9],"and":[10,38,102,111,131],"SemTag,":[11],"an":[12],"application":[13],"written":[14],"on":[15],"the":[16,49,58,67,76,80,83,100,115,133,136],"to":[18,29,48,73,92],"perform":[19],"automated":[20,121],"semantic":[21,45,70,116,124,137],"tagging":[22,71,125],"of":[23,32,82,96,114,126,135],"large":[24,122],"corpora.":[25],"We":[26,118],"apply":[27],"SemTag":[28,84],"collection":[31],"approximately":[33,40],"264":[34],"million":[35,42,60],"web":[36,50],"pages,":[37],"generate":[39],"434":[41,59],"automatically":[43],"disambiguated":[44],"tags,":[46],"published":[47],"as":[51],"label":[53],"bureau":[54],"providing":[55],"metadata":[56],"regarding":[57],"annotations.":[61],"To":[62],"our":[63,104],"knowledge,":[64],"this":[65],"is":[66],"largest":[68],"scale":[69,123],"effort":[72],"date.We":[74],"describe":[75,86],"Seeker":[77],"platform,":[78],"discuss":[79],"architecture":[81],"application,":[85],"new":[88],"disambiguation":[89,95],"algorithm":[90],"specialized":[91],"support":[93],"ontological":[94],"data,":[98],"evaluate":[99],"algorithm,":[101],"present":[103],"final":[105],"results":[106],"with":[107],"information":[108],"about":[109],"acquiring":[110],"making":[112],"use":[113],"tags.":[117],"argue":[119],"that":[120],"ambiguous":[127],"content":[128],"can":[129],"bootstrap":[130],"accelerate":[132],"creation":[134],"web.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":23}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}