{"id":"https://openalex.org/W150801922","doi":null,"title":"Automatically Extracting Structure from Free Text Addresses.","display_name":"Automatically Extracting Structure from Free Text Addresses.","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W150801922","mag":"150801922"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.1741","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.1741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/disc/disc01/out/websites/deb_december/borkar.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5071095413","display_name":"Vinayak Borkar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinayak Borkar","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104316716","display_name":"Kaustubh Deshmukh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaustubh Deshmukh","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031035935","display_name":"Sunita Sarawagi","orcid":"https://orcid.org/0009-0005-9538-6616","observed_orcids":["https://orcid.org/0009-0005-9538-6616"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunita Sarawagi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":30.2444,"has_fulltext":false,"cited_by_count":316,"citation_normalized_percentile":{"value":0.99814717,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"23","issue":null,"first_page":"27","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8208000063896179,"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":0.8208000063896179,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.17649999260902405,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00039999998989515007,"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/structured-information-extraction","display_name":"structured data extraction","score":0.6790000200271606},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.8840000033378601},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/rule-based-approach","display_name":"rule-based methods","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9179414510726929},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5281424522399902},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5127702355384827},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45470649003982544},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.44185057282447815},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3288552165031433},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2971605360507965},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13980424404144287},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.109.1741","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.109.1741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sigmod.org/disc/disc01/out/websites/deb_december/borkar.pdf","raw_type":"text"},{"id":"mag:150801922","doi":null,"is_oa":false,"landing_page_url":"https://www.csd.uoc.gr/~hy460/pdf/franklin.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S62003192","display_name":"IEEE Data(base) Engineering Bulletin","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IEEE Data(base) Engineering Bulletin","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1483744472","https://openalex.org/W1524002271","https://openalex.org/W1552081212","https://openalex.org/W1553019137","https://openalex.org/W1848127982","https://openalex.org/W2020147322","https://openalex.org/W2024770506","https://openalex.org/W2097345556","https://openalex.org/W2109149785","https://openalex.org/W2120754641","https://openalex.org/W2125838338","https://openalex.org/W2143349571","https://openalex.org/W2150698190","https://openalex.org/W2151826520","https://openalex.org/W2153072229","https://openalex.org/W2153752143","https://openalex.org/W2157637666","https://openalex.org/W2164433331","https://openalex.org/W2170468103","https://openalex.org/W2201552871","https://openalex.org/W2296677182"],"related_works":["https://openalex.org/W2338243862","https://openalex.org/W3004248957","https://openalex.org/W2773398246","https://openalex.org/W2160490056","https://openalex.org/W7128326441","https://openalex.org/W4285219406","https://openalex.org/W2534478988","https://openalex.org/W6960151251","https://openalex.org/W49708911","https://openalex.org/W3005625484"],"abstract_inverted_index":{"In":[0,40],"this":[1],"paper":[2],"we":[3],"present":[4,88],"a":[5,15,83,89,107,122],"novel":[6],"way":[7],"to":[8,82,138],"automatically":[9],"elementize":[10],"postal":[11,85,128],"addresses":[12,129,135],"seen":[13],"as":[14],"plain":[16],"text":[17],"string":[18],"into":[19],"atomic":[20],"structured":[21],"elements":[22],"like":[23],"\u201dCity":[24],"\u201d":[25],"and":[26,49,75,130],"\u201dStreet":[27],"name\u201d.":[28],"This":[29],"is":[30],"an":[31],"essential":[32],"step":[33],"in":[34],"all":[35],"warehouse":[36],"data":[37,110],"cleaning":[38],"activities.":[39],"spite":[41],"of":[42,46,118,126],"the":[43,47,50,58],"practical":[44],"importance":[45],"problem":[48],"technical":[51],"challenges":[52],"it":[53],"offers,":[54],"research":[55],"effort":[56,79],"on":[57,68,113,121,133],"topic":[59],"has":[60],"been":[61],"limited.":[62],"Existing":[63],"commercial":[64],"approaches":[65,71],"are":[66,73],"based":[67,93],"hand-tuned,":[69],"rule-based":[70],"that":[72,95,136],"brittle":[74],"require":[76],"extensive":[77],"manual":[78],"when":[80,104],"moved":[81],"different":[84],"system.":[86],"We":[87],"Hidden":[90],"Markov":[91],"Model":[92],"approach":[94],"can":[96],"work":[97],"with":[98,106],"just":[99],"about":[100],"any":[101],"address":[102],"domain":[103],"seeded":[105],"small":[108],"training":[109],"set.":[111],"Experiments":[112],"real-life":[114],"datasets":[115],"yield":[116],"accuracy":[117],"89":[119],"%":[120,132],"heterogeneous":[123],"nationwide":[124],"database":[125],"Indian":[127],"99.6":[131],"US":[134],"tend":[137],"be":[139],"more":[140],"templatized.":[141],"1":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":17}],"updated_date":"2026-09-12T09:15:50.089291","created_date":"2016-06-24T00:00:00"}