{"id":"https://openalex.org/W4402777266","doi":"https://doi.org/10.1080/13658816.2024.2405182","title":"Toponym resolution leveraging lightweight and open-source large language models and geo-knowledge","display_name":"Toponym resolution leveraging lightweight and open-source large language models and geo-knowledge","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4402777266","doi":"https://doi.org/10.1080/13658816.2024.2405182"},"language":"en","primary_location":{"id":"doi:10.1080/13658816.2024.2405182","is_oa":true,"landing_page_url":"https://doi.org/10.1080/13658816.2024.2405182","pdf_url":null,"source":{"id":"https://openalex.org/S4210181446","display_name":"International Journal of Geographical Information Systems","issn_l":"0269-3798","issn":["0269-3798","1362-3087"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Geographical Information Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1080/13658816.2024.2405182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022428964","display_name":"Xuke Hu","orcid":"https://orcid.org/0000-0002-5649-0243"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Xuke Hu","raw_affiliation_strings":["Institute of Data Science, German Aerospace Center (DLR)","Institute of Data Science, German Aerospace Center (DLR), Jena, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5649-0243","affiliations":[{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR)","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR), Jena, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046349685","display_name":"Jens Kersten","orcid":"https://orcid.org/0000-0002-4735-7360"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Kersten","raw_affiliation_strings":["Institute of Data Science, German Aerospace Center (DLR)","Institute of Data Science, German Aerospace Center (DLR), Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR)","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR), Jena, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080030614","display_name":"Friederike Klan","orcid":"https://orcid.org/0000-0002-1856-7334"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Friederike Klan","raw_affiliation_strings":["Institute of Data Science, German Aerospace Center (DLR)","Institute of Data Science, German Aerospace Center (DLR), Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR)","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institute of Data Science, German Aerospace Center (DLR), Jena, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103160969","display_name":"Sheikh Mastura Farzana","orcid":"https://orcid.org/0000-0003-4242-2458"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210087817","display_name":"Software (Germany)","ror":"https://ror.org/004g36n56","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210087817"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sheikh Mastura Farzana","raw_affiliation_strings":["Institute of Software Technology, German Aerospace Center (DLR)","Institute of Software Technology, German Aerospace Center (DLR), Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software Technology, German Aerospace Center (DLR)","institution_ids":["https://openalex.org/I2898391981"]},{"raw_affiliation_string":"Institute of Software Technology, German Aerospace Center (DLR), Cologne, Germany","institution_ids":["https://openalex.org/I2898391981","https://openalex.org/I4210087817"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022428964"],"corresponding_institution_ids":["https://openalex.org/I2898391981"],"apc_list":null,"apc_paid":null,"fwci":9.6596,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.98414127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"40","issue":"3","first_page":"670","last_page":"697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.993399977684021,"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/T12881","display_name":"linguistics and terminology studies","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.960099995136261,"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":0.6069053411483765},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5685756206512451},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.4758967161178589},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4037863314151764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23194554448127747},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.17209655046463013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069053411483765},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5685756206512451},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4758967161178589},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4037863314151764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23194554448127747},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17209655046463013},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/13658816.2024.2405182","is_oa":true,"landing_page_url":"https://doi.org/10.1080/13658816.2024.2405182","pdf_url":null,"source":{"id":"https://openalex.org/S4210181446","display_name":"International Journal of Geographical Information Systems","issn_l":"0269-3798","issn":["0269-3798","1362-3087"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Geographical Information Science","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:208870","is_oa":true,"landing_page_url":"https://doi.org/10.1080/13658816.2024.2405182>.","pdf_url":"https://elib.dlr.de/208870/1/Toponym%20resolution%20leveraging%20lightweight%20and%20open-source%20large%20language%20models%20and%20geoknowledge.pdf","source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.1080/13658816.2024.2405182","is_oa":true,"landing_page_url":"https://doi.org/10.1080/13658816.2024.2405182","pdf_url":null,"source":{"id":"https://openalex.org/S4210181446","display_name":"International Journal of Geographical Information Systems","issn_l":"0269-3798","issn":["0269-3798","1362-3087"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Geographical Information Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1490960179","https://openalex.org/W1516184288","https://openalex.org/W2003094793","https://openalex.org/W2080133951","https://openalex.org/W2088091054","https://openalex.org/W2141835599","https://openalex.org/W2152229249","https://openalex.org/W2226371358","https://openalex.org/W2251896305","https://openalex.org/W2574923006","https://openalex.org/W2593537191","https://openalex.org/W2593831809","https://openalex.org/W2594284271","https://openalex.org/W2755127771","https://openalex.org/W2788931857","https://openalex.org/W2789215765","https://openalex.org/W2799089834","https://openalex.org/W2897725449","https://openalex.org/W2972978497","https://openalex.org/W2973135148","https://openalex.org/W2973619314","https://openalex.org/W2979524927","https://openalex.org/W2996857645","https://openalex.org/W3104532573","https://openalex.org/W3104748221","https://openalex.org/W3111371400","https://openalex.org/W3139007848","https://openalex.org/W3161200389","https://openalex.org/W3209721572","https://openalex.org/W3214659126","https://openalex.org/W4206981623","https://openalex.org/W4211026163","https://openalex.org/W4230918692","https://openalex.org/W4250763916","https://openalex.org/W4281689570","https://openalex.org/W4284713202","https://openalex.org/W4287887524","https://openalex.org/W4292083459","https://openalex.org/W4296550267","https://openalex.org/W4309651804","https://openalex.org/W4318679823","https://openalex.org/W4382246105","https://openalex.org/W4383860783","https://openalex.org/W4384525653","https://openalex.org/W4387344566","https://openalex.org/W4387460165","https://openalex.org/W4387929070","https://openalex.org/W4388184973","https://openalex.org/W4390100500","https://openalex.org/W4391136507","https://openalex.org/W4393002303","https://openalex.org/W4401555054","https://openalex.org/W4402364221","https://openalex.org/W6600168044","https://openalex.org/W6600403287","https://openalex.org/W6601013545","https://openalex.org/W6608782863","https://openalex.org/W6712725667","https://openalex.org/W6756688054","https://openalex.org/W6839910382"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Toponym":[0],"resolution":[1],"is":[2,47,119],"crucial":[3],"for":[4,195,201],"extracting":[5],"geographic":[6],"information":[7],"from":[8],"natural":[9],"language":[10,64],"texts,":[11],"such":[12],"as":[13,131],"social":[14],"media":[15],"posts":[16],"and":[17,33,61,66,80,102,111,150,170,198,204,208],"news":[18],"articles.":[19],"Despite":[20],"the":[21,142,154,164,171,209],"advancements":[22],"in":[23,99,212],"current":[24],"methods,":[25,42,130],"including":[26,137],"state-of-the-art":[27],"deep":[28],"learning":[29],"solutions":[30],"like":[31],"GENRE":[32,207],"a":[34,55,115],"sophisticated":[35],"voting":[36,174,210],"system":[37,175,211],"that":[38,58],"integrates":[39],"seven":[40,134],"individual":[41,166],"further":[43],"enhancing":[44],"their":[45,93,104],"accuracy":[46],"essential.":[48],"To":[49],"achieve":[50],"this":[51],"goal,":[52],"we":[53,69,96],"propose":[54],"novel":[56],"method":[57,144,156],"combines":[59],"lightweight":[60],"open-source":[62],"large":[63],"models":[65,197],"geo-knowledge.":[67],"Specifically,":[68,153],"first":[70],"fine-tune":[71],"Mistral":[72],"(7B),":[73,75],"Baichuan2":[74],"Llama2":[76],"(7B":[77],"&":[78],"13B),":[79],"Falcon":[81],"(7B)":[82],"to":[83,127],"estimate":[84],"toponyms\u2019":[85],"unambiguous":[86],"reference":[87],"(e.g.,":[88],"city,":[89],"state,":[90],"country)":[91],"given":[92],"contexts.":[94],"Subsequently,":[95],"correct":[97],"inaccuracies":[98],"generated":[100],"references":[101],"determine":[103],"geo-coordinates":[105],"via":[106],"sequentially":[107],"querying":[108],"GeoNames,":[109],"Nominatim,":[110],"ArcGIS":[112],"geocoders":[113],"until":[114],"successful":[116],"geocoding":[117],"result":[118],"achieved.":[120],"Our":[121],"methods":[122,180],"demonstrate":[123],"enhanced":[124],"performance":[125],"compared":[126],"20":[128],"existing":[129],"evidenced":[132],"across":[133],"challenging":[135],"datasets":[136],"83,365":[138],"toponyms":[139],"worldwide,":[140],"with":[141],"Mistral-based":[143,155],"leading,":[145],"followed":[146],"by":[147,168,176],"Baichuan2,":[148],"Llama2,":[149],"Falcon-based":[151],"methods.":[152],"achieves":[157],"an":[158],"Accuracy@161km":[159],"of":[160],"0.91,":[161],"surpassing":[162],"GENRE,":[163],"best":[165],"method,":[167],"17%":[169],"seven-methods":[172],"composite":[173],"7%.":[177],"Moreover,":[178],"our":[179],"are":[181],"computationally":[182],"efficient,":[183],"operable":[184],"on":[185],"one":[186],"general":[187],"GPU,":[188],"have":[189],"modest":[190],"memory":[191],"requirements":[192],"(14":[193],"GB":[194,200],"7B":[196],"27":[199],"13B":[202],"models),":[203],"exceed":[205],"both":[206],"inferring":[213],"speed.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}
