{"id":"https://openalex.org/W4390100357","doi":"https://doi.org/10.1145/3589132.3625618","title":"GPT Applications in Relevance Model Training in Map Search","display_name":"GPT Applications in Relevance Model Training in Map Search","publication_year":2023,"publication_date":"2023-11-13","ids":{"openalex":"https://openalex.org/W4390100357","doi":"https://doi.org/10.1145/3589132.3625618"},"language":"en","primary_location":{"id":"doi:10.1145/3589132.3625618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589132.3625618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589132.3625618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589132.3625618","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083039718","display_name":"Renzhong Wang","orcid":"https://orcid.org/0009-0008-4503-1173"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renzhong Wang","raw_affiliation_strings":["Microsoft, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040267673","display_name":"Maryam Omidi Najafabadi","orcid":"https://orcid.org/0000-0003-1830-7660"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Najafabadi","raw_affiliation_strings":["Microsoft, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010058688","display_name":"Chiqun Zhang","orcid":"https://orcid.org/0000-0003-4332-6126"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiqun Zhang","raw_affiliation_strings":["Microsoft, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103085131","display_name":"Long-Qi Chen","orcid":"https://orcid.org/0000-0003-0505-0560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long-Qi Chen","raw_affiliation_strings":["Microsoft, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093559167","display_name":"Tanya Olenina","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Olenina","raw_affiliation_strings":["Microsoft, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065508800","display_name":"Dragomir Yankov","orcid":"https://orcid.org/0009-0006-4509-3222"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dragomir Yankov","raw_affiliation_strings":["Microsoft, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, United States","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67191055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9980999827384949,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9977999925613403,"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":0.8494131565093994},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.8011823892593384},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7513309121131897},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7460620403289795},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6556510925292969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5576357245445251},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5541818141937256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.542270839214325},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5282874703407288},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5241092443466187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5085612535476685},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4871658980846405},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47773000597953796},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4417165219783783},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.433609277009964},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3982880711555481},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39281395077705383},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3752777576446533}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494131565093994},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8011823892593384},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7513309121131897},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7460620403289795},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6556510925292969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5576357245445251},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5541818141937256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542270839214325},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5282874703407288},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5241092443466187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5085612535476685},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4871658980846405},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47773000597953796},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4417165219783783},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.433609277009964},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3982880711555481},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39281395077705383},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3752777576446533},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589132.3625618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589132.3625618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589132.3625618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3589132.3625618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589132.3625618","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589132.3625618","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390100357.pdf","grobid_xml":"https://content.openalex.org/works/W4390100357.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2028870587","https://openalex.org/W2293478687","https://openalex.org/W2989321829","https://openalex.org/W4226278401","https://openalex.org/W4309652662"],"related_works":["https://openalex.org/W2786391746","https://openalex.org/W4287644835","https://openalex.org/W2143806604","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W4381430104","https://openalex.org/W2995102745","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W1990237101"],"abstract_inverted_index":{"Understanding":[0],"map":[1],"queries":[2],"and":[3,45,81,121,151,168,199],"retrieving":[4],"correct":[5],"entity":[6],"results":[7],"are":[8,18,60],"the":[9],"two":[10],"main":[11],"relevance":[12,169],"tasks":[13],"in":[14,62,90,159,208],"Map":[15],"search.":[16],"They":[17],"usually":[19],"performed":[20],"by":[21,93,183],"a":[22,43,100,114,188,200,210],"set":[23],"of":[24,33,102],"task":[25,137,173],"specific":[26,138,174],"machine":[27],"learning":[28],"models.":[29],"Collecting":[30],"large":[31],"amount":[32],"high":[34],"quality":[35],"labelled":[36],"data":[37,57,119,123,129,181,193],"for":[38,54,84,104,117],"training":[39],"such":[40,140],"models":[41,77,139,175],"is":[42],"time-consuming":[44],"labor-intensive":[46],"process.":[47],"Although":[48],"various":[49,136],"methods":[50],"have":[51,86],"been":[52],"studied":[53],"producing":[55],"pseudo":[56],"labels,":[58],"they":[59],"limited":[61],"their":[63],"effectiveness":[64],"when":[65,176],"applied":[66],"across":[67,171],"different":[68],"languages":[69],"or":[70,178],"tasks.":[71],"The":[72],"recently":[73],"released":[74],"Large":[75],"Language":[76],"(LLMs),":[78],"including":[79],"ChatGPT":[80],"GPT-4":[82],"(GPT":[83],"short),":[85],"demonstrated":[87],"state-of-the-art":[88],"performance":[89],"text":[91],"understanding":[92],"using":[94],"simple":[95],"prompt":[96,201],"instructions":[97],"with":[98,196],"only":[99],"handful":[101],"examples":[103],"in-context":[105],"learning.":[106],"In":[107],"this":[108,132],"paper,":[109],"we":[110,126,186],"explore":[111],"GPT":[112,155,195,206],"as":[113,141],"cost-effective":[115],"alternative":[116],"both":[118],"labeling":[120],"synthetic":[122],"generation,":[124],"where":[125],"subsequently":[127],"use":[128],"obtained":[130],"from":[131,194],"approach":[133],"to":[134,204],"train":[135],"maps":[142],"intent":[143],"detection,":[144,146],"address":[145,147],"parsing,":[148],"geo-entity":[149],"ranking,":[150],"rank":[152],"scores":[153],"calibration.":[154],"demonstrates":[156],"strong":[157],"potential":[158],"generating":[160],"otherwise":[161],"hard-to-synthesize":[162],"data.":[163],"We":[164],"observe":[165],"significant":[166],"accuracy":[167],"improvement":[170],"all":[172],"trained":[177],"fine-tuned":[179],"on":[180],"generated":[182],"GPT.":[184],"Lastly,":[185],"propose":[187],"general":[189],"framework":[190],"combining":[191],"labeled":[192],"other":[197],"sources":[198],"fine-tune":[202],"structure":[203],"guide":[205],"model":[207],"completing":[209],"given":[211],"task.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}