{"id":"https://openalex.org/W4389575478","doi":"https://doi.org/10.1145/3615890.3628538","title":"Is ChatGPT a game changer for geocoding - a benchmark for geocoding address parsing techniques","display_name":"Is ChatGPT a game changer for geocoding - a benchmark for geocoding address parsing techniques","publication_year":2023,"publication_date":"2023-11-13","ids":{"openalex":"https://openalex.org/W4389575478","doi":"https://doi.org/10.1145/3615890.3628538"},"language":"en","primary_location":{"id":"doi:10.1145/3615890.3628538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615890.3628538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615890.3628538","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3615890.3628538","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028652882","display_name":"Zhengcong Yin","orcid":"https://orcid.org/0000-0001-7199-5517"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengcong Yin","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-7199-5517","affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070880857","display_name":"Diya Li","orcid":null},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diya Li","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0002-3287-9385","affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033315714","display_name":"Daniel W. Goldberg","orcid":"https://orcid.org/0000-0001-9304-7139"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel W. Goldberg","raw_affiliation_strings":["Texas A&M University, College Station, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-9304-7139","affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, Texas, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":21.2193,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.99409158,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9976999759674072,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geocoding","display_name":"Geocoding","score":0.9360643625259399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8085034489631653},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7059390544891357},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6589933633804321},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6432561874389648},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.52763432264328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251280725002289},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3916447162628174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37257635593414307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33281823992729187},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10134485363960266},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.08617031574249268},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08407032489776611}],"concepts":[{"id":"https://openalex.org/C42629822","wikidata":"https://www.wikidata.org/wiki/Q1346408","display_name":"Geocoding","level":2,"score":0.9360643625259399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085034489631653},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7059390544891357},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6589933633804321},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6432561874389648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.52763432264328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251280725002289},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3916447162628174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37257635593414307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33281823992729187},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10134485363960266},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.08617031574249268},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08407032489776611},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3615890.3628538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615890.3628538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615890.3628538","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3615890.3628538","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3615890.3628538","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3615890.3628538","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389575478.pdf","grobid_xml":"https://content.openalex.org/works/W4389575478.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W49724729","https://openalex.org/W1566289585","https://openalex.org/W1600611951","https://openalex.org/W2020694859","https://openalex.org/W2043177955","https://openalex.org/W2082534483","https://openalex.org/W2110025586","https://openalex.org/W2168367617","https://openalex.org/W2171512372","https://openalex.org/W2240573979","https://openalex.org/W2514316054","https://openalex.org/W2595551253","https://openalex.org/W2757470890","https://openalex.org/W2790570950","https://openalex.org/W2964520675","https://openalex.org/W2966051858","https://openalex.org/W2989321829","https://openalex.org/W2992845944","https://openalex.org/W3022208712","https://openalex.org/W3041474538","https://openalex.org/W3110303792","https://openalex.org/W3211446437","https://openalex.org/W4293657050","https://openalex.org/W4309651788"],"related_works":["https://openalex.org/W10590203","https://openalex.org/W3125352268","https://openalex.org/W1829360400","https://openalex.org/W1978785994","https://openalex.org/W2920874770","https://openalex.org/W2004610910","https://openalex.org/W2610881451","https://openalex.org/W1921424391","https://openalex.org/W2996283026","https://openalex.org/W3124130683"],"abstract_inverted_index":{"The":[0,151,183],"remarkable":[1],"success":[2],"of":[3,18,64,79,114,135,214],"GPT":[4],"models":[5,167,172],"across":[6,105],"various":[7],"tasks,":[8,234],"including":[9],"toponymy":[10],"recognition":[11],"motivates":[12],"us":[13],"to":[14,117,178,231],"assess":[15],"the":[16,19,23,31,47,133,136,161,179,193,210],"performance":[17,36,134,145,163],"GPT-3":[20,137,169,184],"model":[21,138,158,226],"in":[22,37,83,139,188,192],"geocoding":[24,57,81],"address":[25,66,97,141,194],"parsing":[26,195],"task.":[27],"To":[28],"ensure":[29],"that":[30,99,155,219],"evaluation":[32,54,152],"more":[33],"accurately":[34],"mirrors":[35],"real-world":[38],"scenarios":[39],"with":[40,146,197,204],"diverse":[41],"user":[42],"input":[43,72,77,90],"qualities":[44],"and":[45,92,110,112,123,131,148,168,212],"resolve":[46],"pressing":[48],"need":[49],"for":[50,56,202,224],"a":[51,61,80],"`gold":[52],"standard'":[53],"dataset":[55,63,86],"systems,":[58],"we":[59,129],"introduce":[60],"benchmark":[62],"low-quality":[65],"descriptions":[67],"synthesized":[68],"based":[69],"on":[70,127],"human":[71],"patterns":[73],"mining":[74],"from":[75,103],"actual":[76],"logs":[78],"system":[82],"production.":[84],"This":[85],"has":[87,159],"21":[88],"different":[89],"errors":[91],"variations;":[93],"contains":[94],"over":[95,164],"239,000":[96],"records":[98],"are":[100],"uniquely":[101],"selected":[102],"streets":[104],"all":[106],"U.S.":[107],"50":[108],"states":[109],"D.C.;":[111],"consists":[113],"three":[115],"subsets":[116],"be":[118],"used":[119],"as":[120,236],"training,":[121],"validation,":[122],"testing":[124],"sets.":[125],"Building":[126],"this,":[128],"train":[130],"gauge":[132],"extracting":[140],"components,":[142],"contrasting":[143],"its":[144],"transformer-based":[147,166],"LSTM-based":[149],"models.":[150],"results":[153,176],"indicate":[154],"Bidirectional":[156,180],"LSTM-CRF":[157,181],"achieved":[160],"best":[162],"these":[165],"model.":[170,182],"Transformer-based":[171],"demonstrate":[173],"very":[174],"comparable":[175],"compared":[177],"model,":[185],"though":[186],"trailing":[187],"performance,":[189],"showcases":[190],"potential":[191],"task":[196],"few-shot":[198],"examples,":[199],"exhibiting":[200],"room":[201],"improvement":[203],"additional":[205],"fine-tuning.":[206],"We":[207],"open":[208],"source":[209],"code":[211],"data":[213],"this":[215],"presented":[216],"benchmark1":[217],"so":[218],"researchers":[220],"can":[221],"utilize":[222],"it":[223,230],"future":[225],"development":[227],"or":[228],"extend":[229],"evaluate":[232],"similar":[233],"such":[235],"document":[237],"geocoding.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}