{"id":"https://openalex.org/W2154838933","doi":"https://doi.org/10.1145/1265530.1265538","title":"Decision trees for entity identification","display_name":"Decision trees for entity identification","publication_year":2007,"publication_date":"2007-06-11","ids":{"openalex":"https://openalex.org/W2154838933","doi":"https://doi.org/10.1145/1265530.1265538","mag":"2154838933"},"language":"en","primary_location":{"id":"doi:10.1145/1265530.1265538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1265530.1265538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","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/A5008813690","display_name":"Venkatesan T. Chakaravarthy","orcid":"https://orcid.org/0000-0002-9422-7243"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Venkatesan T. Chakaravarthy","raw_affiliation_strings":["IBM India Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037155424","display_name":"Vinayaka Pandit","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayaka Pandit","raw_affiliation_strings":["IBM India Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110192164","display_name":"Sambuddha Roy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sambuddha Roy","raw_affiliation_strings":["IBM India Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056617357","display_name":"Pranjal Awasthi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranjal Awasthi","raw_affiliation_strings":["IBM India Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_strings":["IBM India Research Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9991000294685364,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9991000294685364,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.996999979019165,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/set","display_name":"Set (abstract data type)","score":0.5630253553390503},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5530392527580261},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.5291025042533875},{"id":"https://openalex.org/keywords/binary-decision-diagram","display_name":"Binary decision diagram","score":0.5175582766532898},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.5155860781669617},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5074364542961121},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.501288652420044},{"id":"https://openalex.org/keywords/conjecture","display_name":"Conjecture","score":0.5006601810455322},{"id":"https://openalex.org/keywords/expected-value","display_name":"Expected value","score":0.4821586012840271},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.4737425744533539},{"id":"https://openalex.org/keywords/binary-search-tree","display_name":"Binary search tree","score":0.46480193734169006},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4470149278640747},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42388346791267395},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4173157811164856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3906356692314148},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35538655519485474},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1820361316204071}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5630253553390503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5530392527580261},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.5291025042533875},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.5175582766532898},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.5155860781669617},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5074364542961121},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.501288652420044},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.5006601810455322},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.4821586012840271},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.4737425744533539},{"id":"https://openalex.org/C91154448","wikidata":"https://www.wikidata.org/wiki/Q623818","display_name":"Binary search tree","level":3,"score":0.46480193734169006},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4470149278640747},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42388346791267395},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4173157811164856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3906356692314148},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35538655519485474},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1820361316204071},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"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:10.1145/1265530.1265538","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1265530.1265538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.01RUT_INST:11663598150004646","is_oa":false,"landing_page_url":"https://scholarship.libraries.rutgers.edu/esploro/outputs/conferenceProceeding/Decision-trees-for-entity-identification/991031654793104646","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W19752829","https://openalex.org/W154081573","https://openalex.org/W1479863711","https://openalex.org/W1604945782","https://openalex.org/W1780185704","https://openalex.org/W1843157236","https://openalex.org/W1970074386","https://openalex.org/W2003159902","https://openalex.org/W2011039300","https://openalex.org/W2011896212","https://openalex.org/W2018571947","https://openalex.org/W2061143573","https://openalex.org/W2071622814","https://openalex.org/W2105497083","https://openalex.org/W2111828334","https://openalex.org/W2132852269","https://openalex.org/W2133431834","https://openalex.org/W2134331592","https://openalex.org/W2145117280","https://openalex.org/W2151596305","https://openalex.org/W2798428635","https://openalex.org/W3141776272","https://openalex.org/W3184666341","https://openalex.org/W6628682275","https://openalex.org/W6636181864"],"related_works":["https://openalex.org/W2056975861","https://openalex.org/W2363556447","https://openalex.org/W2089900921","https://openalex.org/W270522628","https://openalex.org/W2501849745","https://openalex.org/W2539085113","https://openalex.org/W1510719821","https://openalex.org/W2011933350","https://openalex.org/W3169685561","https://openalex.org/W1978536651"],"abstract_inverted_index":{"We":[0,128,146,196],"consider":[1,147],"the":[2,39,45,48,68,73,99,108,112,118,122,130,142,165,172,204,220],"problem":[3,82,132,205],"of":[4,26,32,41,47,50,76,101,124,144,157,167,175,178,209,222,244],"constructing":[5],"decision":[6,59],"trees":[7],"for":[8,213,219],"entity":[9,64],"identification":[10,92],"from":[11],"a":[12,19,24,29,35,58,148,185,207,241,246],"given":[13],"relational":[14],"table.":[15],"The":[16,53,181],"input":[17,113,135],"is":[18,55,78,115,126,164,171,184,191,200,228],"table":[20,114],"containing":[21],"information":[22],"about":[23],"set":[25,31,40,123,143],"entities":[27,42,125,168],"over":[28,38,121,141],"fixed":[30],"attributes":[33],"and":[34,95,117,137,152,169],"probability":[36,119,139],"distribution":[37,120],"that":[43,61,72,198],"specifies":[44],"likelihood":[46],"occurrence":[49],"each":[51,63],"entity.":[52],"goal":[54],"to":[56,202,231],"construct":[57],"tree":[60],"identifies":[62],"unambiguously":[65],"by":[66,249],"testing":[67],"attribute":[69],"values":[70,177],"such":[71,84],"average":[74],"number":[75,166,174],"tests":[77],"minimized.":[79],"This":[80],"classical":[81],"finds":[83],"diverse":[85],"applications":[86],"as":[87],"efficient":[88,96],"fault":[89],"detection,":[90],"species":[91],"in":[93,98],"biology,":[94],"diagnosis":[97],"field":[100],"medicine.":[102],"Prior":[103],"work":[104],"mainly":[105],"deals":[106],"with":[107],"special":[109],"case":[110,221],"where":[111,162],"binary":[116,214,223],"uniform.":[127],"study":[129],"general":[131],"involving":[133],"arbitrary":[134,138],"tables":[136,215],"distributions":[140],"entities.":[145],"natural":[149],"greedy":[150],"algorithm":[151,227],"prove":[153],"an":[154,179],"approximation":[155,226],"guarantee":[156],"O(rK":[158],"\u2022":[159],"log":[160,194],"N),":[161,211],"N":[163],"K":[170],"maximum":[173],"distinct":[176],"attribute.":[180],"value":[182],"rK":[183],"suitably":[186],"defined":[187],"Ramsey":[188],"number,":[189],"which":[190],"at":[192],"most":[193],"K.":[195],"show":[197],"it":[199],"NP-hard":[201],"approximate":[203],"within":[206],"factor":[208],"\u03a9(log":[210],"even":[212],"(i.e.":[216],"K=2).":[217],"Thus,":[218],"tables,":[224],"our":[225,238],"optimal":[229],"up":[230],"constant":[232],"factors":[233],"(since":[234],"r2=2).":[235],"In":[236],"addition,":[237],"analysis":[239],"indicates":[240],"possible":[242],"way":[243],"resolving":[245],"Ramsey-theoretic":[247],"conjecture":[248],"Erdos.":[250]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}