{"id":"https://openalex.org/W2063876610","doi":"https://doi.org/10.1145/1077501.1077516","title":"Approximate matching of textual domain attributes for information source integration","display_name":"Approximate matching of textual domain attributes for information source integration","publication_year":2005,"publication_date":"2005-06-17","ids":{"openalex":"https://openalex.org/W2063876610","doi":"https://doi.org/10.1145/1077501.1077516","mag":"2063876610"},"language":"en","primary_location":{"id":"doi:10.1145/1077501.1077516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1077501.1077516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international workshop on Information quality in information systems","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/A5073960712","display_name":"Andreas Koeller","orcid":null},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andreas Koeller","raw_affiliation_strings":["Montclair State University, Montclair, NJ"],"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031725619","display_name":"Vinay Keelara","orcid":null},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Keelara","raw_affiliation_strings":["Montclair State University, Montclair, NJ"],"affiliations":[{"raw_affiliation_string":"Montclair State University, Montclair, NJ","institution_ids":["https://openalex.org/I166088655"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073960712"],"corresponding_institution_ids":["https://openalex.org/I166088655"],"apc_list":null,"apc_paid":null,"fwci":0.435,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6873151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","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/T10215","display_name":"Semantic Web and Ontologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7923519611358643},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6375728845596313},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5743674635887146},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5725682377815247},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5725038647651672},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5635961294174194},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5635794401168823},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5432743430137634},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46858900785446167},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4676840901374817},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.4366244077682495},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.427490770816803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21726953983306885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11214157938957214},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08949115872383118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7923519611358643},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6375728845596313},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5743674635887146},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5725682377815247},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5725038647651672},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5635961294174194},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5635794401168823},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5432743430137634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46858900785446167},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4676840901374817},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.4366244077682495},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.427490770816803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21726953983306885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11214157938957214},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08949115872383118},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1077501.1077516","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1077501.1077516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd international workshop on Information quality in information systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7900000214576721,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W122885654","https://openalex.org/W168287280","https://openalex.org/W204601728","https://openalex.org/W1549531352","https://openalex.org/W1592609929","https://openalex.org/W1781748254","https://openalex.org/W1833785989","https://openalex.org/W1881756506","https://openalex.org/W2001560228","https://openalex.org/W2008896880","https://openalex.org/W2038281398","https://openalex.org/W2042389627","https://openalex.org/W2075085482","https://openalex.org/W2076291573","https://openalex.org/W2094407133","https://openalex.org/W2094951520","https://openalex.org/W2096461223","https://openalex.org/W2099725016","https://openalex.org/W2126850915","https://openalex.org/W2132610455","https://openalex.org/W2138745488","https://openalex.org/W2138755792","https://openalex.org/W2168929226","https://openalex.org/W2169948249","https://openalex.org/W2188351697","https://openalex.org/W2283581966","https://openalex.org/W2322994051","https://openalex.org/W2328546698","https://openalex.org/W4251369550","https://openalex.org/W6606832361","https://openalex.org/W6635494053"],"related_works":["https://openalex.org/W2355440778","https://openalex.org/W2064717691","https://openalex.org/W2164160537","https://openalex.org/W2372493300","https://openalex.org/W2391399503","https://openalex.org/W4244644848","https://openalex.org/W2341628596","https://openalex.org/W2110778011","https://openalex.org/W4255070144","https://openalex.org/W2171244245"],"abstract_inverted_index":{"A":[0],"key":[1],"problem":[2,108],"in":[3,100],"the":[4,10,107],"integration":[5],"of":[6,12,109,116,128],"information":[7,45],"sources":[8,46],"is":[9,35],"identification":[11],"related":[13,91],"attributes":[14,92,115],"or":[15,121],"objects":[16],"across":[17,55,74,93],"independent":[18,75,95],"sources.":[19],"Inferring":[20],"such":[21,31,50],"meta-information":[22],"from":[23],"source":[24],"data":[25],"(rather":[26],"than":[27],"a-priori":[28],"available":[29],"meta-data,":[30],"as":[32,51],"attribute":[33],"names)":[34],"sometimes":[36],"possible.":[37],"For":[38],"example,":[39],"existing":[40],"algorithms":[41],"attempt":[42],"to":[43],"integrate":[44],"by":[47],"finding":[48],"patterns":[49,70],"Inclusion":[52],"Dependencies":[53],"(INDs)":[54],"them.":[56],"However,":[57],"INDs":[58],"are":[59,66],"based":[60,97],"on":[61,98],"exact":[62],"set":[63],"inclusion":[64],"and":[65,85,131],"thus":[67],"very":[68],"strict":[69],"that":[71,88,118],"rarely":[72],"hold":[73],"real-world":[76],"databases.We":[77],"propose":[78],"two":[79,94],"error-tolerant":[80],"measures,":[81],"termed":[82],"Similarity":[83],"Score":[84],"Distribution":[86],"Score,":[87],"help":[89],"identify":[90],"databases,":[96],"similarities":[99],"their":[101],"data.":[102],"Those":[103],"measures":[104,130],"specifically":[105],"address":[106],"identifying":[110],"semantic":[111],"relationships":[112],"between":[113],"textual":[114],"databases":[117],"have":[119],"few":[120],"no":[122],"equal":[123],"values.We":[124],"also":[125],"present":[126],"implementations":[127],"those":[129],"some":[132],"experimental":[133],"results.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}