{"id":"https://openalex.org/W4386212598","doi":"https://doi.org/10.1109/siu59756.2023.10223996","title":"Deep Active Learning for Address Parsing Tasks with BERT","display_name":"Deep Active Learning for Address Parsing Tasks with BERT","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4386212598","doi":"https://doi.org/10.1109/siu59756.2023.10223996"},"language":"en","primary_location":{"id":"doi:10.1109/siu59756.2023.10223996","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu59756.2023.10223996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Signal Processing and Communications Applications Conference (SIU)","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/A5112988682","display_name":"Berkay G\u00fcler","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]},{"id":"https://openalex.org/I71443028","display_name":"Donaldson (United States)","ror":"https://ror.org/02p7bfx81","country_code":"US","type":"company","lineage":["https://openalex.org/I71443028"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Berkay G\u00fcler","raw_affiliation_strings":["Donald Bren School of Information and Computer Sciences University of California,Irvine,California,USA","Donald Bren School of Information and Computer Sciences University of California, Irvine, California, USA"],"affiliations":[{"raw_affiliation_string":"Donald Bren School of Information and Computer Sciences University of California,Irvine,California,USA","institution_ids":["https://openalex.org/I71443028"]},{"raw_affiliation_string":"Donald Bren School of Information and Computer Sciences University of California, Irvine, California, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006724754","display_name":"Bet\u00fcl Ayg\u00fcn","orcid":"https://orcid.org/0000-0001-5191-9664"},"institutions":[{"id":"https://openalex.org/I4210088664","display_name":"Turkish Society of Hematology","ror":"https://ror.org/003pzts41","country_code":"TR","type":"other","lineage":["https://openalex.org/I4210088664"]},{"id":"https://openalex.org/I4210152669","display_name":"Teknoloji Arastirma ve Gelistirme Endustriyel Urunler Bilisim Teknolojileri San Tic","ror":"https://ror.org/040nc8096","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210152669"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Bet\u00fcl Ayg\u00fcn","raw_affiliation_strings":["Huawei Turkey Research and Development Center,Istanbul,Turkey","Huawei Turkey Research and Development Center, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Huawei Turkey Research and Development Center,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210152669","https://openalex.org/I4210088664"]},{"raw_affiliation_string":"Huawei Turkey Research and Development Center, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024873860","display_name":"Ayd\u0131n Gerek","orcid":"https://orcid.org/0000-0001-9875-7041"},"institutions":[{"id":"https://openalex.org/I4210152669","display_name":"Teknoloji Arastirma ve Gelistirme Endustriyel Urunler Bilisim Teknolojileri San Tic","ror":"https://ror.org/040nc8096","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210152669"]},{"id":"https://openalex.org/I4210088664","display_name":"Turkish Society of Hematology","ror":"https://ror.org/003pzts41","country_code":"TR","type":"other","lineage":["https://openalex.org/I4210088664"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ayd\u0131n Gerek","raw_affiliation_strings":["Huawei Turkey Research and Development Center,Istanbul,Turkey","Huawei Turkey Research and Development Center, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Huawei Turkey Research and Development Center,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210152669","https://openalex.org/I4210088664"]},{"raw_affiliation_string":"Huawei Turkey Research and Development Center, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041143722","display_name":"Alaeddin Sel\u00e7uk G\u00fcrel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088664","display_name":"Turkish Society of Hematology","ror":"https://ror.org/003pzts41","country_code":"TR","type":"other","lineage":["https://openalex.org/I4210088664"]},{"id":"https://openalex.org/I4210152669","display_name":"Teknoloji Arastirma ve Gelistirme Endustriyel Urunler Bilisim Teknolojileri San Tic","ror":"https://ror.org/040nc8096","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210152669"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Alaeddin Sel\u00e7uk G\u00fcrel","raw_affiliation_strings":["Huawei Turkey Research and Development Center,Istanbul,Turkey","Huawei Turkey Research and Development Center, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Huawei Turkey Research and Development Center,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210152669","https://openalex.org/I4210088664"]},{"raw_affiliation_string":"Huawei Turkey Research and Development Center, Istanbul, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112988682"],"corresponding_institution_ids":["https://openalex.org/I204250578","https://openalex.org/I71443028"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55405688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.975600004196167,"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":0.8491668701171875},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7297788262367249},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7231080532073975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7070435285568237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6285821795463562},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5921581387519836},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5413389801979065},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5339763164520264},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5074042677879333},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.48253294825553894},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33812880516052246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491668701171875},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7297788262367249},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7231080532073975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7070435285568237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6285821795463562},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5921581387519836},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5413389801979065},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5339763164520264},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5074042677879333},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.48253294825553894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33812880516052246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu59756.2023.10223996","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu59756.2023.10223996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3046984657","https://openalex.org/W2053943328","https://openalex.org/W2056314584","https://openalex.org/W34092691","https://openalex.org/W1492505081","https://openalex.org/W2365028544","https://openalex.org/W4309984931","https://openalex.org/W2949671220","https://openalex.org/W4282977123","https://openalex.org/W1986633584"],"abstract_inverted_index":{"Deep":[0],"learning":[1,68,75,97],"models":[2],"tend":[3],"to":[4,19,37,48,60,65,77,172,176],"perform":[5],"better":[6],"with":[7,106,126,148,158],"larger":[8],"datasets.":[9],"With":[10],"decreasing":[11],"data":[12,36,87],"handling":[13],"costs,":[14,162,185],"researchers":[15],"have":[16],"the":[17,31,54,79,92,166,188],"means":[18],"gather":[20],"and":[21,82,129],"store":[22],"vast":[23],"amounts":[24],"of":[25,53,94,168,191],"unlabeled":[26,86],"data.":[27,56],"Supervised":[28],"learning,":[29],"on":[30,110,140,146],"other":[32],"hand,":[33],"requires":[34],"training":[35],"be":[38],"labeled":[39],"by":[40],"annotators.":[41],"However,":[42],"high":[43],"annotation":[44,161],"costs":[45],"pose":[46],"challenges":[47],"labeling":[49,184],"an":[50,111],"optimum":[51],"portion":[52],"available":[55],"One":[57],"proposed":[58],"method":[59],"mitigate":[61],"this":[62],"problem":[63],"is":[64],"employ":[66],"active":[67,96],"(AL).":[69],"AL":[70,124,135,154,173],"strategies":[71,181],"use":[72],"a":[73,100,107],"machine":[74],"model":[76,109],"select":[78,177],"most":[80],"informative":[81],"representative":[83],"samples":[84],"among":[85],"points.":[88],"Here,":[89],"we":[90],"demonstrate":[91],"effectiveness":[93],"uncertainty-based":[95],"strategies,":[98],"including":[99],"new":[101],"strategy,":[102],"for":[103,118,155],"address":[104,114,156],"parsing":[105,157],"BERT":[108,159],"in-house":[112],"Arabic":[113],"dataset":[115,141],"manually":[116],"annotated":[117],"two":[119],"different":[120],"tasks.":[121],"We":[122,132,151],"compare":[123],"methods":[125],"random":[127],"sampling":[128],"longest-sentence":[130],"baselines.":[131],"show":[133],"that":[134,153],"strategies'":[136],"usefulness":[137],"greatly":[138],"depends":[139],"characteristics,":[142],"being":[143],"less":[144],"effective":[145],"datasets":[147],"fewer":[149],"classes.":[150],"conclude":[152],"decreases":[160],"if":[163],"measured":[164,186],"in":[165,187],"number":[167,190],"queries.":[169],"Yet,":[170],"due":[171],"methods'":[174],"tendency":[175],"longer":[178],"queries,":[179],"some":[180],"may":[182],"increase":[183],"total":[189],"words.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}