{"id":"https://openalex.org/W2069318033","doi":"https://doi.org/10.1109/icde.2010.5447820","title":"Efficient identification of coupled entities in document collections","display_name":"Efficient identification of coupled entities in document collections","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2069318033","doi":"https://doi.org/10.1109/icde.2010.5447820","mag":"2069318033"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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/A5000660268","display_name":"Nikos Sarkas","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nikos Sarkas","raw_affiliation_strings":["University of Toronto, Canada","University Of Toronto , USA"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University Of Toronto , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050138372","display_name":"Albert Angel","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Albert Angel","raw_affiliation_strings":["University of Toronto, Canada","University Of Toronto , USA"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University Of Toronto , USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035257754","display_name":"Nick Koudas","orcid":"https://orcid.org/0000-0001-5648-0638"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Koudas","raw_affiliation_strings":["University of Toronto, Canada","University Of Toronto , USA"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University Of Toronto , USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT and T Research Laboratories, USA","AT&T Lab. Res., USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000660268"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":3.4685,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93845182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":null,"first_page":"769","last_page":"772"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","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/T10538","display_name":"Data Mining Algorithms and Applications","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/T11106","display_name":"Data Management and Algorithms","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7733758687973022},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6834091544151306},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6211001873016357},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.6024373769760132},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.5833004713058472},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.411440372467041},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37644895911216736},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3501203656196594},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3338783383369446},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07426401972770691}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7733758687973022},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6834091544151306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6211001873016357},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.6024373769760132},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.5833004713058472},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.411440372467041},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37644895911216736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3501203656196594},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3338783383369446},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07426401972770691},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2010.5447820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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":11,"referenced_works":["https://openalex.org/W167149422","https://openalex.org/W1506285740","https://openalex.org/W1514949376","https://openalex.org/W2097776316","https://openalex.org/W2114731047","https://openalex.org/W2116780029","https://openalex.org/W2210278139","https://openalex.org/W6606719542","https://openalex.org/W6630198464","https://openalex.org/W6630762386","https://openalex.org/W6677145740"],"related_works":["https://openalex.org/W2386723501","https://openalex.org/W2387879414","https://openalex.org/W2390304029","https://openalex.org/W2354923724","https://openalex.org/W2146830340","https://openalex.org/W2377101853","https://openalex.org/W2362180844","https://openalex.org/W2105573916","https://openalex.org/W2378405797","https://openalex.org/W4391230627"],"abstract_inverted_index":{"The":[0],"relentless":[1],"pace":[2],"at":[3],"which":[4],"textual":[5],"data":[6],"are":[7],"generated":[8],"on-line":[9],"necessitates":[10],"novel":[11],"paradigms":[12],"for":[13,25,87,97,104],"their":[14],"understanding":[15],"and":[16,73,94],"exploration.":[17],"To":[18],"this":[19],"end,":[20],"we":[21],"introduce":[22],"a":[23,38],"methodology":[24],"discovering":[26],"strong":[27,91],"entity":[28,92,102],"associations":[29,93],"in":[30,67],"all":[31,89],"the":[32,46,55,68,99,108],"slices":[33],"(meta-data":[34],"value":[35],"restrictions)":[36],"of":[37,49,57,77,81,107],"document":[39,69,109],"collection.":[40,70,110],"Since":[41],"related":[42],"documents":[43],"mention":[44],"approximately":[45],"same":[47],"group":[48],"core":[50,83],"entities":[51,59],"(people,":[52],"locations,":[53],"etc.),":[54],"groups":[56],"coupled":[58],"discovered":[60],"can":[61],"be":[62],"used":[63],"to":[64],"expose":[65],"themes":[66],"We":[71],"devise":[72],"evaluate":[74],"algorithms":[75],"capable":[76],"addressing":[78],"two":[79],"flavors":[80],"our":[82],"problem:":[84],"algorithm":[85,95],"THR-ENT":[86],"computing":[88,98],"sufficiently":[90],"TOP-ENT":[96],"top-k":[100],"strongest":[101],"associations,":[103],"each":[105],"slice":[106]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}