{"id":"https://openalex.org/W2111625757","doi":"https://doi.org/10.1145/775047.775099","title":"Learning domain-independent string transformation weights for high accuracy object identification","display_name":"Learning domain-independent string transformation weights for high accuracy object identification","publication_year":2002,"publication_date":"2002-07-23","ids":{"openalex":"https://openalex.org/W2111625757","doi":"https://doi.org/10.1145/775047.775099","mag":"2111625757"},"language":"en","primary_location":{"id":"doi:10.1145/775047.775099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775047.775099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth 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/A5033888618","display_name":"Sheila Tejada","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheila Tejada","raw_affiliation_strings":["University of Southern, California, Marina del Rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern, California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089542402","display_name":"Craig A. Knoblock","orcid":"https://orcid.org/0000-0002-6371-4807"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig A. Knoblock","raw_affiliation_strings":["University of Southern, California, Marina del Rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern, California, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801204180","https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045363082","display_name":"Steven Minton","orcid":"https://orcid.org/0000-0001-8640-2905"},"institutions":[{"id":"https://openalex.org/I2801840469","display_name":"Torch Technologies (United States)","ror":"https://ror.org/00nrhr905","country_code":"US","type":"company","lineage":["https://openalex.org/I2801840469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Minton","raw_affiliation_strings":["Fetch Technologies, Marina del Rey, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fetch Technologies, Marina del Rey, CA","institution_ids":["https://openalex.org/I2801840469"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.8421,"has_fulltext":false,"cited_by_count":256,"citation_normalized_percentile":{"value":0.99598743,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8268845081329346},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6665863990783691},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6364232897758484},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6033056974411011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5981975793838501},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5951472520828247},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.593919575214386},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5926053524017334},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5530755519866943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5354499816894531},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5040246844291687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44359642267227173},{"id":"https://openalex.org/keywords/atlas","display_name":"Atlas (anatomy)","score":0.41546013951301575},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.38191133737564087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37020760774612427},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3250799775123596},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11971390247344971},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10713750123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268845081329346},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6665863990783691},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6364232897758484},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6033056974411011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5981975793838501},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5951472520828247},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.593919575214386},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5926053524017334},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5530755519866943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5354499816894531},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5040246844291687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44359642267227173},{"id":"https://openalex.org/C2776673561","wikidata":"https://www.wikidata.org/wiki/Q655357","display_name":"Atlas (anatomy)","level":2,"score":0.41546013951301575},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.38191133737564087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37020760774612427},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3250799775123596},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11971390247344971},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10713750123977661},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/775047.775099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/775047.775099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.2186","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unsw.edu.au/~qzhang/papers/143.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W177885090","https://openalex.org/W1484228408","https://openalex.org/W1569123402","https://openalex.org/W1612155886","https://openalex.org/W1997841190","https://openalex.org/W2010595692","https://openalex.org/W2018616927","https://openalex.org/W2018770010","https://openalex.org/W2020191321","https://openalex.org/W2036216970","https://openalex.org/W2038281398","https://openalex.org/W2073471108","https://openalex.org/W2080402044","https://openalex.org/W2096717389","https://openalex.org/W2127674618","https://openalex.org/W2138589588","https://openalex.org/W2139578439","https://openalex.org/W2158030545","https://openalex.org/W2170902582","https://openalex.org/W4285719527","https://openalex.org/W4299822035","https://openalex.org/W6603574123"],"related_works":["https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W4398785990","https://openalex.org/W2092552144","https://openalex.org/W2943461603","https://openalex.org/W2354196777","https://openalex.org/W2257399947","https://openalex.org/W2965473297","https://openalex.org/W2386746909","https://openalex.org/W2108265183"],"abstract_inverted_index":{"The":[0,12,135],"task":[1],"of":[2,37,44,51,84,120,123],"object":[3,38,73],"identification":[4,39,74],"occurs":[5],"when":[6],"integrating":[7],"information":[8],"from":[9],"multiple":[10],"websites.":[11],"same":[13],"data":[14],"objects":[15,30],"can":[16,63],"exist":[17],"in":[18,94],"inconsistent":[19],"text":[20,33],"formats":[21],"across":[22,153],"sites,":[23],"making":[24],"it":[25,113],"difficult":[26],"to":[27,88,96,106,114,116,126],"identify":[28,97],"matching":[29,98],"using":[31],"exact":[32],"match.":[34],"Previous":[35],"methods":[36,152],"have":[40,70],"required":[41],"manual":[42,49,61],"construction":[43],"domain-specific":[45],"string":[46,86],"transformations":[47,87,125],"or":[48],"setting":[50],"general":[52,124],"transformation":[53],"parameter":[54],"weights":[55,119],"for":[56],"recognizing":[57],"format":[58],"inconsistencies.":[59],"This":[60],"process":[62],"be":[64],"time":[65],"consuming":[66],"and":[67,145],"error-prone.":[68],"We":[69],"developed":[71],"an":[72],"system":[75],"called":[76],"Active":[77,108],"Atlas":[78,109],"[18],":[79],"which":[80,111],"applies":[81],"a":[82,121,127],"set":[83,122],"domain-independent":[85],"compare":[89],"the":[90,107,118],"objects'":[91],"shared":[92],"attributes":[93],"order":[95],"objects.":[99],"In":[100],"this":[101,140],"paper,":[102],"we":[103],"discuss":[104],"extensions":[105],"system,":[110],"allow":[112],"learn":[115],"tailor":[117],"specific":[128],"application":[129,155],"domain":[130],"through":[131],"limited":[132],"user":[133,148],"input.":[134],"experimental":[136],"results":[137],"demonstrate":[138],"that":[139],"approach":[141],"achieves":[142],"higher":[143],"accuracy":[144],"requires":[146],"less":[147],"involvement":[149],"than":[150],"previous":[151],"various":[154],"domains.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":14}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}