{"id":"https://openalex.org/W1983231745","doi":"https://doi.org/10.1145/1921659.1921661","title":"Decision trees for entity identification","display_name":"Decision trees for entity identification","publication_year":2011,"publication_date":"2011-03-01","ids":{"openalex":"https://openalex.org/W1983231745","doi":"https://doi.org/10.1145/1921659.1921661","mag":"1983231745"},"language":"en","primary_location":{"id":"doi:10.1145/1921659.1921661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1921659.1921661","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","raw_type":"journal-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/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, Vasanth Kunj, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Vasanth Kunj, New Delhi, India","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, Vasanth Kunj, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Vasanth Kunj, New Delhi, India","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, Vasanth Kunj, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Vasanth Kunj, New Delhi, India","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/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranjal Awasthi","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA","Carnegie-Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie-Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"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 K. Mohania","raw_affiliation_strings":["IBM India Research Lab, Vasanth Kunj, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Vasanth Kunj, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7255,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.86196822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9961000084877014,"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":0.9936000108718872,"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/mathematics","display_name":"Mathematics","score":0.5998249053955078},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5763480067253113},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.49904346466064453},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.49732473492622375},{"id":"https://openalex.org/keywords/binary-decision-diagram","display_name":"Binary decision diagram","score":0.4913088381290436},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.48794955015182495},{"id":"https://openalex.org/keywords/expected-value","display_name":"Expected value","score":0.4820895493030548},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.47005048394203186},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.46439439058303833},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45894116163253784},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4209740459918976},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.41801583766937256},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.41217565536499023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3556426763534546},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32506656646728516},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20499250292778015}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5998249053955078},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5763480067253113},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.49904346466064453},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.49732473492622375},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.4913088381290436},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.48794955015182495},{"id":"https://openalex.org/C141042865","wikidata":"https://www.wikidata.org/wiki/Q200125","display_name":"Expected value","level":2,"score":0.4820895493030548},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.47005048394203186},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.46439439058303833},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45894116163253784},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4209740459918976},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.41801583766937256},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.41217565536499023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3556426763534546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32506656646728516},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20499250292778015},{"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},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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:10.1145/1921659.1921661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1921659.1921661","pdf_url":null,"source":{"id":"https://openalex.org/S137348503","display_name":"ACM Transactions on Algorithms","issn_l":"1549-6325","issn":["1549-6325","1549-6333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:alma.01RUT_INST:11663586980004646","is_oa":false,"landing_page_url":"https://scholarship.libraries.rutgers.edu/esploro/outputs/journalArticle/Decision-trees-for-entity-identification/991031654949104646","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":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W19752829","https://openalex.org/W154081573","https://openalex.org/W1479863711","https://openalex.org/W1507980525","https://openalex.org/W1565530450","https://openalex.org/W1604945782","https://openalex.org/W1780185704","https://openalex.org/W1811083715","https://openalex.org/W1843157236","https://openalex.org/W1970074386","https://openalex.org/W2003159902","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/W2154838933","https://openalex.org/W2561675875","https://openalex.org/W2798428635","https://openalex.org/W4244259932","https://openalex.org/W4386628099","https://openalex.org/W6628682275","https://openalex.org/W6636181864","https://openalex.org/W6682291466"],"related_works":["https://openalex.org/W4300631294","https://openalex.org/W2390183607","https://openalex.org/W2766238494","https://openalex.org/W2100521573","https://openalex.org/W847339734","https://openalex.org/W1523494361","https://openalex.org/W2105067139","https://openalex.org/W1930446896","https://openalex.org/W2017311532","https://openalex.org/W4386287458"],"abstract_inverted_index":{"We":[0,128,146,202],"consider":[1,147],"the":[2,39,45,48,68,73,99,108,112,118,122,130,142,169,176,210,228],"problem":[3,82,132,211],"of":[4,26,32,41,47,50,76,101,124,144,157,171,179,182,215,230,254],"constructing":[5],"decision":[6,59],"trees":[7],"for":[8,220,227],"entity":[9,64],"identification":[10,92],"from":[11],"a":[12,19,24,29,35,58,148,190,213,251,256],"given":[13],"relational":[14],"table.":[15],"The":[16,53,185],"input":[17,113,135],"is":[18,55,78,115,126,168,175,189,196,206,236],"table":[20,114],"containing":[21],"information":[22],"about":[23],"set":[25,31,40,123,143],"entities":[27,42,125,172],"over":[28,38,121,141],"fixed":[30],"attributes":[33],"and":[34,95,117,137,152,173],"probability":[36,119,139],"distribution":[37,120],"that":[43,61,72,204],"specifies":[44],"likelihood":[46],"occurrence":[49],"each":[51,63],"entity.":[52],"goal":[54],"to":[56,208,239],"construct":[57],"tree":[60],"identifies":[62],"unambiguously":[65],"by":[66,259],"testing":[67],"attribute":[69],"values":[70,181],"such":[71,84],"average":[74],"number":[75,170,178],"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":[110,229],"where":[111,166],"binary":[116,221,231],"uniform.":[127],"study":[129],"general":[131],"involving":[133],"arbitrary":[134,138],"tables":[136,222],"distributions":[140],"entities.":[145],"natural":[149],"greedy":[150],"algorithm":[151,235],"prove":[153],"an":[154,183],"approximation":[155,234],"guarantee":[156],"O":[158],"(":[159],"r":[160,187,243],"K":[161,174,188,200,224],"\u22c5":[162],"log":[163,199],"N":[164,167,217],"),":[165,218],"maximum":[177],"distinct":[180],"attribute.":[184],"value":[186],"suitably":[191],"defined":[192],"Ramsey":[193],"number,":[194],"which":[195],"at":[197],"most":[198],".":[201],"show":[203],"it":[205],"NP-hard":[207],"approximate":[209],"within":[212],"factor":[214],"\u03a9(log":[216],"even":[219],"(i.e.,":[223],"=2).":[225,245],"Thus,":[226],"tables,":[232],"our":[233,248],"optimal":[237],"up":[238],"constant":[240],"factors":[241],"(since":[242],"2":[244],"In":[246],"addition,":[247],"analysis":[249],"indicates":[250],"possible":[252],"way":[253],"resolving":[255],"Ramsey-theoretic":[257],"conjecture":[258],"Erd\u00f6s.":[260]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}