{"id":"https://openalex.org/W4399157460","doi":"https://doi.org/10.5194/agile-giss-5-12-2024","title":"Enhancing toponym identification: Leveraging Topo-BERT and open-source data to differentiate between toponyms and extract spatial relationships","display_name":"Enhancing toponym identification: Leveraging Topo-BERT and open-source data to differentiate between toponyms and extract spatial relationships","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399157460","doi":"https://doi.org/10.5194/agile-giss-5-12-2024"},"language":"en","primary_location":{"id":"doi:10.5194/agile-giss-5-12-2024","is_oa":true,"landing_page_url":"https://doi.org/10.5194/agile-giss-5-12-2024","pdf_url":"https://agile-giss.copernicus.org/articles/5/12/2024/agile-giss-5-12-2024.pdf","source":{"id":"https://openalex.org/S4210203054","display_name":"AGILE GIScience Series","issn_l":"2700-8150","issn":["2700-8150"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AGILE: GIScience Series","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://agile-giss.copernicus.org/articles/5/12/2024/agile-giss-5-12-2024.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086137427","display_name":"Joseph Shingleton","orcid":"https://orcid.org/0000-0002-1628-3231"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joseph Shingleton","raw_affiliation_strings":["School of Geographical and Earth Sciences, University of Glasgow, Glasgow, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1628-3231","affiliations":[{"raw_affiliation_string":"School of Geographical and Earth Sciences, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076329659","display_name":"Anahid Basiri","orcid":"https://orcid.org/0000-0002-2399-1797"},"institutions":[{"id":"https://openalex.org/I4210128584","display_name":"The Alan Turing Institute","ror":"https://ror.org/035dkdb55","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210128584"]},{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ana Basiri","raw_affiliation_strings":["School of Geographical and Earth Sciences, University of Glasgow, Glasgow, United Kingdom","The Alan Turing Institute, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Geographical and Earth Sciences, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"The Alan Turing Institute, London, United Kingdom","institution_ids":["https://openalex.org/I4210128584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7401,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84461373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9391000270843506,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9221000075340271,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/toponymy","display_name":"Toponymy","score":0.8550341129302979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290332317352295},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.6765466332435608},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6344625949859619},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5469751954078674},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.432138055562973},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4242037236690521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3805347979068756},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35869696736335754},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24088776111602783},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.24083319306373596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.11903536319732666},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.1182507574558258}],"concepts":[{"id":"https://openalex.org/C116856471","wikidata":"https://www.wikidata.org/wiki/Q485762","display_name":"Toponymy","level":2,"score":0.8550341129302979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290332317352295},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.6765466332435608},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6344625949859619},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5469751954078674},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.432138055562973},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4242037236690521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3805347979068756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35869696736335754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24088776111602783},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.24083319306373596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.11903536319732666},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.1182507574558258},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5194/agile-giss-5-12-2024","is_oa":true,"landing_page_url":"https://doi.org/10.5194/agile-giss-5-12-2024","pdf_url":"https://agile-giss.copernicus.org/articles/5/12/2024/agile-giss-5-12-2024.pdf","source":{"id":"https://openalex.org/S4210203054","display_name":"AGILE GIScience Series","issn_l":"2700-8150","issn":["2700-8150"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AGILE: GIScience Series","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:322014","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/72771.html>","pdf_url":"https://eprints.gla.ac.uk/322014/3/322014.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"doi:10.5194/agile-giss-5-12-2024","is_oa":true,"landing_page_url":"https://doi.org/10.5194/agile-giss-5-12-2024","pdf_url":"https://agile-giss.copernicus.org/articles/5/12/2024/agile-giss-5-12-2024.pdf","source":{"id":"https://openalex.org/S4210203054","display_name":"AGILE GIScience Series","issn_l":"2700-8150","issn":["2700-8150"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AGILE: GIScience Series","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3741620067","display_name":null,"funder_award_id":"MR/S01795X/2","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399157460.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W13771447","https://openalex.org/W2063935068","https://openalex.org/W2593537191","https://openalex.org/W2626283244","https://openalex.org/W2739855398","https://openalex.org/W2796495817","https://openalex.org/W2940355763","https://openalex.org/W2948947170","https://openalex.org/W2952087486","https://openalex.org/W2963341956","https://openalex.org/W3102122100","https://openalex.org/W3125937743","https://openalex.org/W3213422511","https://openalex.org/W4234325645","https://openalex.org/W4281885045","https://openalex.org/W4282924243","https://openalex.org/W4306680578","https://openalex.org/W4380433137","https://openalex.org/W4383345515","https://openalex.org/W4385766704"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3172220373","https://openalex.org/W4223915615","https://openalex.org/W2181412350","https://openalex.org/W2737684396","https://openalex.org/W3125223822","https://openalex.org/W1969751626","https://openalex.org/W4220946479","https://openalex.org/W4310608224","https://openalex.org/W2232096346"],"abstract_inverted_index":{"Abstract.":[0],"Geoparsing,":[1],"the":[2,19,30,56,76,111,129,152,161,194,210,216,225],"process":[3],"of":[4,11,23,35,52,59,69,78,81,124,135,156,163,190,209,230],"linking":[5],"locations":[6,208],"within":[7,61,114,151],"text":[8,82,136,153],"to":[9,50,86,109,148,171],"sets":[10],"geographic":[12],"coordinates,":[13],"plays":[14],"an":[15,187],"important":[16],"role":[17],"in":[18,33,122,154,234],"extraction":[20],"and":[21,118,144,197,199,206,220,232],"analysis":[22],"information":[24],"from":[25,38,138],"unstructured":[26],"textual":[27],"data.":[28],"With":[29],"rapid":[31],"growth":[32],"availability":[34],"user-generated":[36],"data":[37,147],"online":[39],"sources,":[40],"there":[41],"is":[42,55,71,107,168],"increasing":[43],"demand":[44],"for":[45],"reliable":[46],"geoparsing":[47],"methods.":[48],"Central":[49],"many":[51],"these":[53,235],"methods":[54],"accurate":[57],"identification":[58,68],"toponyms":[60,70,85,121,150,203],"text.":[62],"For":[63],"some":[64],"applications,":[65],"however,":[66],"simple":[67],"insufficient.":[72],"Problems":[73],"which":[74],"require":[75,90],"association":[77],"a":[79,87,91,101,115,133,173,179],"piece":[80],"containing":[83],"multiple":[84],"singular":[88],"location":[89],"more":[92,217],"nuanced":[93],"approach.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"show":[99],"that":[100],"transformer":[102,174],"based":[103,175],"deep":[104],"learning":[105],"model,":[106],"able":[108],"identify":[110],"subject":[112,162,195],"toponym":[113],"given":[116],"text,":[117],"classify":[119,149],"other":[120],"terms":[123,155],"their":[125,157],"spatial":[126,158],"relationship":[127,159],"with":[128,160,224],"subject.":[130],"We":[131,213],"curate":[132],"dataset":[134,167],"taken":[137],"Wikipedia":[139],"pages":[140],"representing":[141,204],"5252":[142],"locations,":[143],"use":[145],"OpenStreetMap":[146],"each":[164],"article.":[165],"This":[166],"then":[169],"used":[170],"train":[172],"deep-learning":[176],"model.":[177],"On":[178],"human":[180],"labelled":[181],"test":[182],"set,":[183],"our":[184],"model":[185,226],"achieves":[186],"F1":[188,228],"score":[189],"0.916":[191],"when":[192,201],"identifying":[193,202],"toponym,":[196],"0.884":[198],"0.793":[200],"parent":[205],"child":[207],"subject,":[211],"respectively.":[212,237],"also":[214],"consider":[215],"complex":[218],"adjacent":[219],"crossing":[221],"relationships":[222],"-":[223],"achieving":[227],"scores":[229],"0.548":[231],"0.704":[233],"categories,":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
