{"id":"https://openalex.org/W2768960873","doi":"https://doi.org/10.1145/3149858.3149865","title":"A deeply annotated testbed for geographical text analysis","display_name":"A deeply annotated testbed for geographical text analysis","publication_year":2017,"publication_date":"2017-11-07","ids":{"openalex":"https://openalex.org/W2768960873","doi":"https://doi.org/10.1145/3149858.3149865","mag":"2768960873"},"language":"en","primary_location":{"id":"doi:10.1145/3149858.3149865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3149858.3149865","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3149865&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3149865&type=pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058785189","display_name":"Paul Rayson","orcid":"https://orcid.org/0000-0002-1257-2191"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Rayson","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081158436","display_name":"Alex Reinhold","orcid":null},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Reinhold","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002446284","display_name":"James O. Butler","orcid":null},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Butler","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075985782","display_name":"Christopher Donaldson","orcid":"https://orcid.org/0000-0002-2924-3001"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chris Donaldson","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080702364","display_name":"Ian Gregory","orcid":"https://orcid.org/0000-0001-8745-2242"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Gregory","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011578133","display_name":"Joanna E. Taylor","orcid":"https://orcid.org/0000-0001-8597-0097"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joanna Taylor","raw_affiliation_strings":["Lancaster University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67415387"],"apc_list":null,"apc_paid":null,"fwci":12.2635,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9812451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.9891999959945679,"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":0.9891999959945679,"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/T12872","display_name":"Philippine History and Culture","score":0.9211999773979187,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"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":0.9009000062942505,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7828359603881836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323453426361084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6944860219955444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6046173572540283},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.545270562171936},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5312570929527283},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5143736600875854},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5122544169425964},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37182313203811646},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26678889989852905},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22758066654205322}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7828359603881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323453426361084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6944860219955444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046173572540283},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.545270562171936},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5312570929527283},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5143736600875854},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5122544169425964},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37182313203811646},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26678889989852905},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22758066654205322},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3149858.3149865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3149858.3149865","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3149865&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/73293a79-77f1-4d18-b8b7-f11f0de4e311","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/73293a79-77f1-4d18-b8b7-f11f0de4e311","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Rayson, P, Reinhold, A, Butler, J, Donaldson, C, Gregory, I & Taylor, J 2017, A deeply annotated testbed for geographical text analysis: The Corpus of Lake District Writing. in GeoHumanities'17 Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities. Association for Computing Machinery, pp. 9-15. https://doi.org/10.1145/3149858.3149865","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/73293a79-77f1-4d18-b8b7-f11f0de4e311","is_oa":true,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/a-deeply-annotated-testbed-for-geographical-text-analysis-the-corpus-of-lake-district-writing(73293a79-77f1-4d18-b8b7-f11f0de4e311).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rayson, P, Reinhold, A, Butler, J, Donaldson, C, Gregory, I & Taylor, J 2017, A deeply annotated testbed for geographical text analysis: The Corpus of Lake District Writing. in GeoHumanities'17 Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities. Association for Computing Machinery, pp. 9-15. https://doi.org/10.1145/3149858.3149865","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3149858.3149865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3149858.3149865","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3149865&type=pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM SIGSPATIAL Workshop on Geospatial Humanities","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.9200000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3829048491","display_name":null,"funder_award_id":"FP7/2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5200278345","display_name":null,"funder_award_id":"RPG-2015","funder_id":"https://openalex.org/F4320319993","funder_display_name":"Leverhulme Trust"},{"id":"https://openalex.org/G5303011379","display_name":null,"funder_award_id":"EP/R00692X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5593277320","display_name":null,"funder_award_id":"2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5702163051","display_name":null,"funder_award_id":"FP7/2007","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6435515425","display_name":null,"funder_award_id":"RPG-2015-230","funder_id":"https://openalex.org/F4320319993","funder_display_name":"Leverhulme Trust"},{"id":"https://openalex.org/G8580116309","display_name":"Bringing GIS to the Digital Humanities: Defining the Spatial Humanities","funder_award_id":"283850","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320311699","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355"},{"id":"https://openalex.org/F4320319993","display_name":"Leverhulme Trust","ror":"https://ror.org/012mzw131"},{"id":"https://openalex.org/F4320320004","display_name":"British Academy","ror":"https://ror.org/0302b4677"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2768960873.pdf","grobid_xml":"https://content.openalex.org/works/W2768960873.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W172861654","https://openalex.org/W1580289893","https://openalex.org/W1692852022","https://openalex.org/W1969168960","https://openalex.org/W1973312357","https://openalex.org/W1983255417","https://openalex.org/W1986353013","https://openalex.org/W2003094793","https://openalex.org/W2014016288","https://openalex.org/W2056894934","https://openalex.org/W2077555421","https://openalex.org/W2082560607","https://openalex.org/W2096105170","https://openalex.org/W2111938898","https://openalex.org/W2123442489","https://openalex.org/W2188213683","https://openalex.org/W2251559320","https://openalex.org/W2251896305","https://openalex.org/W2494469814","https://openalex.org/W2512173100","https://openalex.org/W2515960978","https://openalex.org/W2554099542","https://openalex.org/W2588853052","https://openalex.org/W2593537191","https://openalex.org/W2593929528","https://openalex.org/W2735735643","https://openalex.org/W2736486661","https://openalex.org/W2810029345","https://openalex.org/W4205359118","https://openalex.org/W4241982274"],"related_works":["https://openalex.org/W629021723","https://openalex.org/W2567355776","https://openalex.org/W2305867964","https://openalex.org/W2394602299","https://openalex.org/W2624106077","https://openalex.org/W3140870753","https://openalex.org/W1994489417","https://openalex.org/W2954189872","https://openalex.org/W1524429405","https://openalex.org/W2020644894"],"abstract_inverted_index":{"This":[0,19,106],"paper":[1],"describes":[2],"the":[3,21,62,65,74,79,84,111,114,152,155,163,176,178,183,186,199,202],"development":[4],"of":[5,23,29,56,71,110,130,154,165,182,201],"an":[6,68],"annotated":[7,34,91],"corpus":[8,89,115,156],"which":[9],"forms":[10],"a":[11,54,158],"challenging":[12],"testbed":[13],"for":[14],"geographical":[15,112,139],"text":[16,184],"analysis":[17],"methods.":[18],"dataset,":[20],"Corpus":[22],"Lake":[24,76],"District":[25,77],"Writing":[26],"(CLDW),":[27],"consists":[28],"80":[30],"manually":[31],"digitised":[32],"and":[33,49,51,59,83,104,127,136,170,194],"texts":[35,43,63],"(comprising":[36],"over":[37],"1.5":[38],"million":[39],"word":[40],"tokens).":[41],"These":[42],"were":[44],"originally":[45],"composed":[46],"between":[47],"1622":[48],"1900,":[50],"they":[52],"represent":[53],"range":[55],"different":[57,125,167,187],"genres":[58],"authors.":[60],"Collectively,":[61],"in":[64],"CLDW":[66],"constitute":[67],"indicative":[69],"sample":[70],"writing":[72],"about":[73],"English":[75],"during":[78],"early":[80,85],"seventeenth":[81],"century":[82],"twentieth":[86],"century.":[87],"The":[88],"is":[90,95,107],"more":[92],"deeply":[93],"than":[94],"currently":[96],"possible":[97],"with":[98],"vanilla":[99],"Named":[100],"Entity":[101],"Recognition,":[102],"Disambiguation":[103],"geoparsing.":[105],"especially":[108],"true":[109],"information":[113],"contains,":[116],"since":[117],"we":[118,150],"have":[119],"undertaken":[120],"not":[121],"only":[122],"to":[123,134,137],"link":[124],"historical":[126],"spelling":[128],"variants":[129],"place-names,":[131],"but":[132],"also":[133],"identify":[135],"differentiate":[138],"features":[140],"such":[141],"as":[142,157],"waterfalls,":[143],"woodlands,":[144],"farms":[145],"or":[146],"inns.":[147],"In":[148,175],"addition,":[149],"illustrate":[151],"potential":[153],"gold":[159,203],"standard":[160,179],"by":[161,185],"evaluating":[162],"results":[164],"three":[166],"NLP":[168,188],"libraries":[169,189],"geoparsers":[171],"on":[172],"its":[173],"contents.":[174],"evaluation,":[177],"NER":[180],"processing":[181],"produces":[190],"many":[191],"false":[192,195],"positive":[193],"negative":[196],"results,":[197],"showing":[198],"strength":[200],"standard.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2017-12-04T00:00:00"}
