{"id":"https://openalex.org/W2118356770","doi":"https://doi.org/10.1145/2339530.2339743","title":"A framework for robust discovery of entity synonyms","display_name":"A framework for robust discovery of entity synonyms","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2118356770","doi":"https://doi.org/10.1145/2339530.2339743","mag":"2118356770"},"language":"en","primary_location":{"id":"doi:10.1145/2339530.2339743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339743","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 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/A5113509258","display_name":"Kaushik Chakrabarti","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaushik Chakrabarti","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613251","display_name":"Tao Cheng","orcid":"https://orcid.org/0000-0001-6250-2581"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Cheng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406351","display_name":"Dong Xin","orcid":"https://orcid.org/0000-0002-1414-9354"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Xin","raw_affiliation_strings":["Google, Kirkland, WA, USA","Google, Kirkland, WA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Kirkland, WA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Kirkland, WA, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113509258"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.9982,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.96271304,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1384","last_page":"1392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9966999888420105,"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/T11106","display_name":"Data Management and Algorithms","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8812288045883179},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.7157254219055176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.678962767124176},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6325397491455078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36515820026397705},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34182339906692505},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12998849153518677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812288045883179},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.7157254219055176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.678962767124176},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6325397491455078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36515820026397705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34182339906692505},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12998849153518677},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2339530.2339743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339743","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 SIGKDD international conference on Knowledge discovery and data mining","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":23,"referenced_works":["https://openalex.org/W100250357","https://openalex.org/W1522404235","https://openalex.org/W1567365482","https://openalex.org/W1574901103","https://openalex.org/W2001496424","https://openalex.org/W2006199065","https://openalex.org/W2046020929","https://openalex.org/W2048351742","https://openalex.org/W2093432797","https://openalex.org/W2100830825","https://openalex.org/W2103296194","https://openalex.org/W2113618143","https://openalex.org/W2153190022","https://openalex.org/W2160555926","https://openalex.org/W2167029568","https://openalex.org/W2167181946","https://openalex.org/W2170741935","https://openalex.org/W2882319491","https://openalex.org/W4245049592","https://openalex.org/W6631164811","https://openalex.org/W6634133269","https://openalex.org/W6651921613","https://openalex.org/W6753056052"],"related_works":["https://openalex.org/W2376156759","https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W2385868535","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2757842199","https://openalex.org/W2389730202","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Entity":[0],"synonyms":[1,24,88,130,141],"are":[2],"critical":[3],"for":[4,59],"many":[5],"applications":[6],"like":[7,37],"information":[8],"retrieval":[9],"and":[10,41,79,152],"named":[11],"entity":[12,23,62,95,107,122,140],"recognition":[13],"in":[14,112,147,149,162],"documents.":[15],"The":[16,139],"current":[17],"trend":[18],"is":[19,146],"to":[20,43,86,103,109],"automatically":[21],"discover":[22,87],"using":[25],"statistical":[26],"techniques":[27,32,81,102],"on":[28,117],"web":[29],"data.":[30],"Prior":[31],"suffer":[33],"from":[34,120],"several":[35],"limitations":[36,72],"click":[38],"log":[39],"sparsity":[40],"inability":[42],"distinguish":[44],"between":[45],"entities":[46],"of":[47,73,128,136],"different":[48,121],"concept":[49],"classes.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,100],"propose":[55,101],"a":[56],"general":[57],"framework":[58,85],"robustly":[60],"discovering":[61],"synonym":[63],"with":[64,97,155],"two":[65],"novel":[66],"similarity":[67],"functions":[68],"that":[69],"overcome":[70],"the":[71,83,125,134,158],"prior":[74],"techniques.":[75],"We":[76],"develop":[77],"efficient":[78],"scalable":[80],"leveraging":[82],"MapReduce":[84],"at":[89],"large":[90],"scale.":[91],"To":[92],"handle":[93],"long":[94,106],"names":[96,108],"extraneous":[98],"tokens,":[99],"effectively":[104],"map":[105],"short":[110],"queries":[111],"query":[113],"log.":[114],"Our":[115],"experiments":[116,156],"real":[118],"data":[119],"domains":[123],"demonstrate":[124],"superior":[126],"quality":[127],"our":[129,137,144],"as":[131,133],"well":[132],"efficiency":[135],"algorithms.":[138],"produced":[142],"by":[143],"system":[145],"production":[148],"Bing":[150],"Shopping":[151],"Video":[153],"search,":[154],"showing":[157],"significance":[159],"it":[160],"brings":[161],"improving":[163],"search":[164],"experience.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}