{"id":"https://openalex.org/W2080437742","doi":"https://doi.org/10.1145/1557019.1557144","title":"Address standardization with latent semantic association","display_name":"Address standardization with latent semantic association","publication_year":2009,"publication_date":"2009-06-28","ids":{"openalex":"https://openalex.org/W2080437742","doi":"https://doi.org/10.1145/1557019.1557144","mag":"2080437742"},"language":"en","primary_location":{"id":"doi:10.1145/1557019.1557144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th 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/A5001909797","display_name":"Honglei Guo","orcid":"https://orcid.org/0000-0002-1485-1987"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglei Guo","raw_affiliation_strings":["IBM China Research Lab., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab., Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110390049","display_name":"Huijia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["IBM China Research Lab., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab., Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725207","display_name":"Zhili Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhili Guo","raw_affiliation_strings":["IBM China Research Lab., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab., Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055590353","display_name":"XiaoXun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XiaoXun Zhang","raw_affiliation_strings":["IBM China Research Lab., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab., Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010426520","display_name":"Zhong Su","orcid":"https://orcid.org/0000-0003-2303-9787"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Su","raw_affiliation_strings":["IBM China Research Lab., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM China Research Lab., Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":1.359,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84764224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1155","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9939000010490417,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.993399977684021,"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/standardization","display_name":"Standardization","score":0.8899956345558167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869669198989868},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6201582551002502},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5342817306518555},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.4782470762729645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501146078109741},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44272828102111816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4181019067764282},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4146472215652466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39156588912010193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3231959044933319},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10131648182868958}],"concepts":[{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.8899956345558167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869669198989868},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6201582551002502},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5342817306518555},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.4782470762729645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501146078109741},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44272828102111816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4181019067764282},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4146472215652466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39156588912010193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3231959044933319},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10131648182868958},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1557019.1557144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1557019.1557144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","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":25,"referenced_works":["https://openalex.org/W77787017","https://openalex.org/W130850236","https://openalex.org/W1513874326","https://openalex.org/W1593045043","https://openalex.org/W1845402413","https://openalex.org/W1880262756","https://openalex.org/W1986544831","https://openalex.org/W1997938337","https://openalex.org/W2029873015","https://openalex.org/W2042980227","https://openalex.org/W2056451646","https://openalex.org/W2087556608","https://openalex.org/W2107743791","https://openalex.org/W2114663556","https://openalex.org/W2124410446","https://openalex.org/W2135892731","https://openalex.org/W2144452292","https://openalex.org/W2144578941","https://openalex.org/W2147152072","https://openalex.org/W2168822971","https://openalex.org/W2426031434","https://openalex.org/W2622248957","https://openalex.org/W4231510805","https://openalex.org/W4233135949","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168","https://openalex.org/W2376963063","https://openalex.org/W2066396794","https://openalex.org/W2366734808","https://openalex.org/W2002476357","https://openalex.org/W2391444248","https://openalex.org/W2390716080"],"abstract_inverted_index":{"Address":[0],"standardization":[1,148,192,232],"is":[2,115,157,178,194],"a":[3,31,116,123,145,181],"very":[4,88],"challenging":[5],"task":[6,120],"in":[7],"data":[8,35,52,86,141,209],"cleansing.":[9],"To":[10],"provide":[11],"better":[12,61],"customer":[13],"relationship":[14],"management":[15],"and":[16,38,50,90,94,118,135,200,219,236],"business":[17],"intelligence":[18],"for":[19,34,62,80,127],"customer-oriented":[20],"cooperates,":[21],"millions":[22],"of":[23,46,54,138,174,211,231],"free-text":[24,146],"addresses":[25],"need":[26,109],"to":[27,30,76,121,159,180],"be":[28],"converted":[29],"standard":[32],"format":[33],"integration,":[36],"de-duplication":[37],"householding.":[39],"Existing":[40],"commercial":[41],"tools":[42],"usually":[43,71,99],"employ":[44],"lots":[45],"hand-craft,":[47],"domain-specific":[48],"rules":[49,59,79],"reference":[51],"dictionary":[53],"cities,":[55],"states":[56],"etc.":[57],"These":[58],"work":[60],"the":[63,136,167,175,190,208,212,224,229],"region":[64],"they":[65],"are":[66,87,100],"designed.":[67],"However,":[68,106],"rule-based":[69,104],"methods":[70,98,108],"require":[72],"more":[73,101],"human":[74,133],"efforts":[75,134,235],"rewrite":[77],"these":[78],"each":[81,128],"new":[82],"domain":[83,177],"since":[84],"address":[85,147,191],"irregular":[89],"varied":[91],"with":[92,150,233],"countries":[93],"regions.":[95],"Supervised":[96],"learning":[97],"adaptable":[102],"than":[103],"approaches.":[105],"supervised":[107],"large-scale":[110,124,217],"labeled":[111,139],"training":[112,140,237],"data.":[113,238],"It":[114],"labor-intensive":[117],"time-consuming":[119],"build":[122],"annotated":[125],"corpus":[126,221],"target":[129,176],"domain.":[130,213],"For":[131],"minimizing":[132],"size":[137],"set,":[142],"we":[143],"present":[144],"method":[149,205,226],"latent":[151,161],"semantic":[152,162],"association":[153,163],"(LaSA).":[154],"LaSA":[155,185,198],"model":[156,186,193],"constructed":[158],"capture":[160],"among":[164],"words":[165],"from":[166,197],"unlabeled":[168],"corpus.":[169],"The":[170,203],"original":[171],"term":[172],"space":[173,183],"projected":[179],"concept":[182],"using":[184],"at":[187],"first,":[188],"then":[189],"active":[195],"learned":[196],"features":[199],"informative":[201],"samples.":[202],"proposed":[204,225],"effectively":[206],"captures":[207],"distribution":[210],"Experimental":[214],"results":[215],"on":[216],"English":[218],"Chinese":[220],"show":[222],"that":[223],"significantly":[227],"enhances":[228],"performance":[230],"less":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}