{"id":"https://openalex.org/W2100869678","doi":"https://doi.org/10.1145/1645953.1645984","title":"Helping editors choose better seed sets for entity set expansion","display_name":"Helping editors choose better seed sets for entity set expansion","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2100869678","doi":"https://doi.org/10.1145/1645953.1645984","mag":"2100869678"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1645984","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1645984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049489150","display_name":"Vishnu Vyas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishnu Vyas","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041476585","display_name":"Patrick Pantel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Pantel","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066954331","display_name":"Eric Crestan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Crestan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":4.8741,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96066539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.7313193082809448},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.7203271389007568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7175661325454712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4939418435096741},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38531774282455444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37746426463127136}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7313193082809448},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7203271389007568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175661325454712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4939418435096741},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38531774282455444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37746426463127136},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1645953.1645984","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1645984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.901.3011","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.901.3011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.patrickpantel.com/download/papers/2009/cikm09a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W78509178","https://openalex.org/W197270748","https://openalex.org/W952881364","https://openalex.org/W1505544955","https://openalex.org/W1930023685","https://openalex.org/W2000251428","https://openalex.org/W2007620009","https://openalex.org/W2009510620","https://openalex.org/W2023736097","https://openalex.org/W2038168073","https://openalex.org/W2045830397","https://openalex.org/W2050078085","https://openalex.org/W2050712820","https://openalex.org/W2056451646","https://openalex.org/W2068737686","https://openalex.org/W2093812930","https://openalex.org/W2097125878","https://openalex.org/W2102029756","https://openalex.org/W2103296194","https://openalex.org/W2117400858","https://openalex.org/W2141099517","https://openalex.org/W2142305207","https://openalex.org/W2157963512","https://openalex.org/W2167181946","https://openalex.org/W2171743956","https://openalex.org/W2271451322","https://openalex.org/W2423725643","https://openalex.org/W2606601345","https://openalex.org/W3035258717","https://openalex.org/W6603254404","https://openalex.org/W6630396373","https://openalex.org/W6940641640"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3209574120","https://openalex.org/W3107602296","https://openalex.org/W4312192474","https://openalex.org/W4210805261","https://openalex.org/W4387297750"],"abstract_inverted_index":{"Sets":[0],"of":[1,19,23,31,43,65,92,149],"named":[2],"entities":[3,20],"are":[4],"used":[5],"heavily":[6],"at":[7],"commercial":[8],"search":[9],"engines":[10],"such":[11],"as":[12],"Google,":[13],"Yahoo":[14],"and":[15,53,99,101,125,169],"Bing.":[16],"Acquiring":[17],"sets":[18,46,168],"typically":[21],"consists":[22],"combining":[24],"semi-supervised":[25,50],"expansion":[26,51,59,107,136,173],"algorithms":[27],"with":[28],"manual":[29],"cleaning":[30],"the":[32,41,63,83,153,164,180],"resulting":[33],"expanded":[34],"sets.":[35,183],"In":[36],"this":[37],"paper,":[38],"we":[39,102,110],"study":[40],"effects":[42,105],"different":[44],"seed":[45,78,86,93,118,128,158,167,182],"in":[47,58,73,139],"a":[48,55,147,157],"state-of-the-art":[49],"system":[52],"show":[54,69],"tremendous":[56],"variation":[57],"performance":[60,174],"depending":[61],"on":[62,106,144,170],"choice":[64],"seeds.":[66],"We":[67,88],"further":[68],"that":[70,135],"human":[71,165],"editors,":[72],"general,":[74],"provide":[75],"very":[76],"bad":[77],"sets,":[79,119],"which":[80,120],"perform":[81],"well-below":[82],"average":[84,145,171],"random":[85],"set.":[87,159],"identify":[89],"three":[90],"factors":[91],"set":[94],"composition,":[95],"namely":[96],"prototypicality,":[97],"ambiguity":[98],"coverage,":[100],"investigate":[103],"their":[104],"performance.":[108],"Finally,":[109],"propose":[111],"various":[112],"automatic":[113,161],"systems":[114],"for":[115],"improving":[116],"editor-generated":[117],"seek":[121],"to":[122,177],"remove":[123],"ambiguous":[124],"other":[126],"error-prone":[127],"instances.":[129],"An":[130],"extensive":[131],"experimental":[132],"analysis":[133],"shows":[134],"quality,":[137],"measured":[138],"R-precision,":[140],"can":[141],"be":[142],"improved":[143],"by":[146,151,175],"maximum":[148],"46%":[150],"removing":[152],"right":[154],"seeds":[155],"from":[156],"Our":[160],"methods":[162],"outperform":[163],"editors":[166],"improve":[172],"up":[176],"34%":[178],"over":[179],"original":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}