{"id":"https://openalex.org/W2057453781","doi":"https://doi.org/10.1145/2666310.2666471","title":"HMM-based address parsing","display_name":"HMM-based address parsing","publication_year":2014,"publication_date":"2014-11-04","ids":{"openalex":"https://openalex.org/W2057453781","doi":"https://doi.org/10.1145/2666310.2666471","mag":"2057453781"},"language":"en","primary_location":{"id":"doi:10.1145/2666310.2666471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666310.2666471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100674281","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-6482-2535"},"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":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Data Research, inome, Inc. and New York University","Data Research, inome, Inc. and New York University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Research, inome, Inc. and New York University","institution_ids":[]},{"raw_affiliation_string":"Data Research, inome, Inc. and New York University#TAB#","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/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":false,"raw_author_name":"Hakan Kardes","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328048","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-9542-2710"},"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":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002868174","display_name":"Ang Sun","orcid":null},"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":false,"raw_author_name":"Ang Sun","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"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":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9491000175476074,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.946399986743927,"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":0.8693705797195435},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7736067771911621},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7438579797744751},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6377015113830566},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5908824801445007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367409586906433},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4636550843715668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4230915904045105},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.412028968334198},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39390677213668823},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07993543148040771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8693705797195435},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7736067771911621},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7438579797744751},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6377015113830566},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5908824801445007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367409586906433},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4636550843715668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4230915904045105},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.412028968334198},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39390677213668823},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07993543148040771},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1145/2666310.2666471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2666310.2666471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"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/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W1974738623"],"abstract_inverted_index":{"Record":[0],"linkage":[1],"is":[2,22,44],"the":[3,17,25,35,45,63,86],"task":[4],"of":[5,24,34,41,90,103],"identifying":[6],"which":[7],"records":[8],"in":[9,30,48],"one":[10,23],"or":[11],"more":[12],"data":[13,95],"collections":[14],"refer":[15],"to":[16,73,100],"same":[18],"entity,":[19],"and":[20,88],"address":[21,58],"most":[26],"commonly":[27],"used":[28],"fields":[29,43],"databases.":[31],"Hence,":[32],"segmentation":[33],"raw":[36],"addresses":[37,104],"into":[38],"a":[39,56],"set":[40],"semantic":[42],"primary":[46],"step":[47],"this":[49,52,91],"task.":[50],"In":[51],"paper,":[53],"we":[54,84],"present":[55],"probabilistic":[57],"parsing":[59],"system":[60,92],"based":[61],"on":[62],"Hidden":[64],"Markov":[65],"Model.":[66],"We":[67],"also":[68],"introduce":[69],"several":[70],"novel":[71],"approaches":[72],"build":[74],"models":[75],"for":[76,93],"noisy":[77],"real-world":[78],"addresses,":[79],"obtaining":[80],"95.6%":[81],"F-measure.":[82],"Furthermore,":[83],"demonstrate":[85],"viability":[87],"efficiency":[89],"large-scale":[94],"by":[96],"scaling":[97],"it":[98],"up":[99],"parse":[101],"billions":[102],"with":[105],"Hadoop.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}