{"id":"https://openalex.org/W4400908819","doi":"https://doi.org/10.1109/siu61531.2024.10601149","title":"Enhancing Address Data Integrity using Transformer-Based Language Models","display_name":"Enhancing Address Data Integrity using Transformer-Based Language Models","publication_year":2024,"publication_date":"2024-05-15","ids":{"openalex":"https://openalex.org/W4400908819","doi":"https://doi.org/10.1109/siu61531.2024.10601149"},"language":"en","primary_location":{"id":"doi:10.1109/siu61531.2024.10601149","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu61531.2024.10601149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11511/110721","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104971356","display_name":"\u00d6mer Faruk K\u00fcrkl\u00fc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u00d6mer Faruk K\u00fcrkl\u00fc","raw_affiliation_strings":["Orta Do&#x011F;&#x0438; Teknik &#x00DC;niversitesi,Modelleme ve Sim&#x00FC;lasyon A.B.D Enformatik Enstit&#x00FC;s&#x00EF;,Ankara,T&#x00FC;rkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orta Do&#x011F;&#x0438; Teknik &#x00DC;niversitesi,Modelleme ve Sim&#x00FC;lasyon A.B.D Enformatik Enstit&#x00FC;s&#x00EF;,Ankara,T&#x00FC;rkiye","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005758418","display_name":"Erdem Akag\u00fcnd\u00fcz","orcid":"https://orcid.org/0000-0002-0792-7306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erdem Akag\u00fcnd\u00fcz","raw_affiliation_strings":["Orta Do&#x011F;&#x0438; Teknik &#x00DC;niversitesi,Modelleme ve Sim&#x00FC;lasyon A.B.D Enformatik Enstit&#x00FC;s&#x00EF;,Ankara,T&#x00FC;rkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orta Do&#x011F;&#x0438; Teknik &#x00DC;niversitesi,Modelleme ve Sim&#x00FC;lasyon A.B.D Enformatik Enstit&#x00FC;s&#x00EF;,Ankara,T&#x00FC;rkiye","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13015567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T11719","display_name":"Data Quality and Management","score":0.9308000206947327,"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":0.9308000206947327,"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":0.6910296678543091},{"id":"https://openalex.org/keywords/data-integrity","display_name":"Data integrity","score":0.5100997090339661},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4875916838645935},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46121299266815186},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.36850202083587646},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2445615530014038},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14082643389701843},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1288902461528778},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07498788833618164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6910296678543091},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.5100997090339661},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4875916838645935},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46121299266815186},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.36850202083587646},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2445615530014038},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14082643389701843},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1288902461528778},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07498788833618164}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/siu61531.2024.10601149","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu61531.2024.10601149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://open.metu.edu.tr:11511/110721","is_oa":true,"landing_page_url":"https://hdl.handle.net/11511/110721","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"32nd IEEE Conference on Signal Processing and Communications Applications, SIU 2024","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:https://open.metu.edu.tr:11511/110721","is_oa":true,"landing_page_url":"https://hdl.handle.net/11511/110721","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"32nd IEEE Conference on Signal Processing and Communications Applications, SIU 2024","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W3089353361","https://openalex.org/W2037795535","https://openalex.org/W4389518428","https://openalex.org/W4387006424","https://openalex.org/W2061818469","https://openalex.org/W9098411","https://openalex.org/W1939743152"],"abstract_inverted_index":{"Address":[0,74],"data":[1],"integrity":[2],"is":[3,12],"a":[4,26,53,61],"critical":[5],"aspect":[6],"in":[7,20,35,89],"numerous":[8],"applications,":[9],"yet":[10],"it":[11],"often":[13],"plagued":[14],"with":[15],"inaccuracies":[16],"and":[17,42,76,93,110],"inconsistencies,":[18],"particularly":[19],"non-standardized":[21],"formats.":[22,112],"This":[23,68],"study":[24],"explores":[25],"novel":[27],"application":[28],"of":[29,44,51,65,101],"transformer-based":[30],"language":[31,36,56],"models,":[32,95],"traditionally":[33],"utilized":[34],"translation":[37],"tasks,":[38],"for":[39],"the":[40,49,72],"standardization":[41],"correction":[43],"Turkish":[45,66],"address":[46,105],"data.":[47],"Leveraging":[48],"capabilities":[50],"Mixtral-8x7B,":[52],"state-of-the-art":[54],"large":[55],"model,":[57],"this":[58],"research":[59],"introduces":[60],"unique,":[62],"handcrafted":[63],"dataset":[64,85],"addresses.":[67],"dataset,":[69],"derived":[70],"from":[71],"National":[73],"Dataset":[75],"enriched":[77],"through":[78],"ChatGPT-4":[79],"to":[80],"simulate":[81],"human-like":[82],"input":[83],"errors.This":[84],"was":[86],"later":[87],"used":[88],"fine-tuning":[90],"both":[91],"TowerInstruct":[92],"T5":[94],"transforming":[96],"them":[97],"into":[98,107],"tools":[99],"capable":[100],"converting":[102],"faulty,":[103],"error-laden":[104],"lines":[106],"standardized,":[108],"structured,":[109],"corrected":[111]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
