{"id":"https://openalex.org/W2028870587","doi":"https://doi.org/10.1145/2663713.2664430","title":"HMM-based Address Parsing with Massive Synthetic Training Data Generation","display_name":"HMM-based Address Parsing with Massive Synthetic Training Data Generation","publication_year":2014,"publication_date":"2014-11-03","ids":{"openalex":"https://openalex.org/W2028870587","doi":"https://doi.org/10.1145/2663713.2664430","mag":"2028870587"},"language":"en","primary_location":{"id":"doi:10.1145/2663713.2664430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2663713.2664430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Location and the Web","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/A5100331094","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-9851-6376"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiang Li","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038628557","display_name":"Hakan Kardes","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Kardes","raw_affiliation_strings":["inome, Inc., Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"inome, Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328117","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-3352-6829"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["inome, Inc., Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"inome, Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002868174","display_name":"Ang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Sun","raw_affiliation_strings":["inome, Inc., Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"inome, Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100331094"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.8591,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.74396522,"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":"33","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9944999814033508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8574424982070923},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8248614072799683},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7080576419830322},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6207522749900818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.595223069190979},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5859072804450989},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46461379528045654},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43276557326316833},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4302995502948761},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4222952425479889},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4185611605644226},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3860380947589874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35647380352020264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574424982070923},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8248614072799683},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7080576419830322},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6207522749900818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595223069190979},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5859072804450989},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46461379528045654},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43276557326316833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4302995502948761},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4222952425479889},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4185611605644226},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3860380947589874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35647380352020264},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2663713.2664430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2663713.2664430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Workshop on Location and the Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.1958","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.1958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unr.edu/%7Ehkardes/pdfs/addressParserTraining.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W2140190241","https://openalex.org/W2143571432","https://openalex.org/W2145948275","https://openalex.org/W2181761791","https://openalex.org/W2240573979"],"related_works":["https://openalex.org/W4312659495","https://openalex.org/W3175965105","https://openalex.org/W4385366257","https://openalex.org/W3101007570","https://openalex.org/W4387910575","https://openalex.org/W3176425421","https://openalex.org/W3091312527","https://openalex.org/W1555087354","https://openalex.org/W4287865546","https://openalex.org/W3007306981"],"abstract_inverted_index":{"Record":[0],"linkage":[1],"is":[2,22,44],"the":[3,17,25,35,45,63,92],"task":[4],"of":[5,24,34,41,73,96,109],"identifying":[6],"which":[7],"records":[8],"in":[9,30,48],"one":[10,23],"or":[11],"more":[12],"data":[13,76,101],"collections":[14],"refer":[15],"to":[16,78,106],"same":[18],"entity,":[19],"and":[20,94],"address":[21,58],"most":[26],"commonly":[27],"used":[28],"fields":[29,43],"databases.":[31],"Hence,":[32],"segmentation":[33],"raw":[36],"addresses":[37],"into":[38],"a":[39,56],"set":[40],"semantic":[42],"primary":[46],"step":[47],"this":[49,52,97],"task.":[50],"In":[51],"paper,":[53],"we":[54,90],"present":[55],"probabilistic":[57],"parsing":[59],"system":[60,98],"based":[61],"on":[62],"Hidden":[64],"Markov":[65],"Model.":[66],"We":[67],"also":[68],"introduce":[69],"several":[70],"novel":[71],"approaches":[72],"synthetic":[74],"training":[75],"generation":[77],"build":[79],"robust":[80],"models":[81],"for":[82,99],"noisy":[83],"real-world":[84],"addresses,":[85],"obtaining":[86],"95.6%":[87],"F-measure.":[88],"Furthermore,":[89],"demonstrate":[91],"viability":[93],"efficiency":[95],"large-scale":[100],"by":[102],"scaling":[103],"it":[104],"up":[105],"parse":[107],"billions":[108],"addresses.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}