{"id":"https://openalex.org/W2115346359","doi":"https://doi.org/10.1145/1557019.1557165","title":"Named entity mining from click-through data using weakly supervised latent dirichlet allocation","display_name":"Named entity mining from click-through data using weakly supervised latent dirichlet allocation","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2115346359","doi":"https://doi.org/10.1145/1557019.1557165","mag":"2115346359"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5111526267","display_name":"Gu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gu Xu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108432183","display_name":"Shuang-Hong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang-Hong Yang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455138","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-5317-7227"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111526267"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":7.2081,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97015813,"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":"1365","last_page":"1374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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":0.9972000122070312,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9000675678253174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8470339775085449},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6346757411956787},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"Click-through rate","score":0.5643763542175293},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5287061929702759},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4593338072299957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43487727642059326},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37522387504577637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37067824602127075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.353790283203125},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2763158082962036}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9000675678253174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470339775085449},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6346757411956787},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.5643763542175293},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5287061929702759},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4593338072299957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43487727642059326},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37522387504577637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37067824602127075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.353790283203125},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2763158082962036},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1557019.1557165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.5722","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.5722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/people/hangli/xu-etal-kdd2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1505083828","https://openalex.org/W1880262756","https://openalex.org/W1990387666","https://openalex.org/W2011859172","https://openalex.org/W2038553416","https://openalex.org/W2042980227","https://openalex.org/W2047221353","https://openalex.org/W2050078085","https://openalex.org/W2064153289","https://openalex.org/W2093812930","https://openalex.org/W2098062695","https://openalex.org/W2107743791","https://openalex.org/W2125771191","https://openalex.org/W2129414564","https://openalex.org/W2131010894","https://openalex.org/W2134510195","https://openalex.org/W2135843591","https://openalex.org/W2141099517","https://openalex.org/W2148540243","https://openalex.org/W2150461699","https://openalex.org/W2163918411","https://openalex.org/W2170741935","https://openalex.org/W2171743956","https://openalex.org/W2613433911","https://openalex.org/W2978329087","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"This":[0,70],"paper":[1,71],"addresses":[2],"Named":[3],"Entity":[4],"Mining":[5],"(NEM),":[6],"in":[7,31,116],"which":[8],"we":[9],"mine":[10],"knowledge":[11],"about":[12],"named":[13,58,108,129,160],"entities":[14],"such":[15],"as":[16,136,144],"movies,":[17],"games,":[18],"and":[19,39,61,94,114,185],"books":[20],"from":[21,102],"a":[22,81,86,140,164],"huge":[23],"amount":[24],"of":[25,57,128],"data.":[26,119],"NEM":[27,74,184],"is":[28],"potentially":[29],"useful":[30],"many":[32],"applications":[33],"including":[34],"web":[35,82],"search,":[36],"online":[37],"advertisement,":[38],"recommender":[40],"system.":[41],"There":[42],"are":[43],"three":[44],"challenges":[45],"for":[46],"the":[47,55,67,91,96,117,122,134,154,177,188],"task:":[48],"finding":[49],"suitable":[50],"data":[51,78,168],"source,":[52],"coping":[53],"with":[54,157],"ambiguities":[56,127],"entity":[59,109,130],"classes,":[60],"incorporating":[62],"necessary":[63],"human":[64],"supervision":[65,101],"into":[66],"mining":[68],"process.":[69],"proposes":[72],"conducting":[73],"by":[75,99,110,132],"using":[76],"click-through":[77,92,118,167],"collected":[79],"at":[80],"search":[83],"engine,":[84],"employing":[85],"topic":[87,97,123,155],"model":[88,98,124,156],"that":[89,176],"generates":[90],"data,":[93],"learning":[95],"weak":[100],"humans.":[103],"Specifically,":[104],"it":[105],"characterizes":[106],"each":[107],"its":[111],"associated":[112],"queries":[113],"URLs":[115],"It":[120,138],"uses":[121],"to":[125,143,151],"resolve":[126],"classes":[131,135],"representing":[133],"topics.":[137],"employs":[139],"method,":[141],"referred":[142],"Weakly":[145],"Supervised":[146],"Latent":[147],"Dirichlet":[148],"Allocation":[149],"(WS-LDA),":[150],"accurately":[152],"learn":[153],"partially":[158],"labeled":[159],"entities.":[161],"Experiments":[162],"on":[163],"large":[165],"scale":[166],"containing":[169],"over":[170],"1.5":[171],"billion":[172],"query-URL":[173],"pairs":[174],"show":[175],"proposed":[178],"approach":[179],"can":[180],"conduct":[181],"very":[182],"accurate":[183],"significantly":[186],"outperforms":[187],"baseline.":[189]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}