{"id":"https://openalex.org/W2736486661","doi":"https://doi.org/10.1145/3078081.3078099","title":"Toponym disambiguation in historical documents using semantic and geographic features","display_name":"Toponym disambiguation in historical documents using semantic and geographic features","publication_year":2017,"publication_date":"2017-06-01","ids":{"openalex":"https://openalex.org/W2736486661","doi":"https://doi.org/10.1145/3078081.3078099","mag":"2736486661"},"language":"en","primary_location":{"id":"doi:10.1145/3078081.3078099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051763204","display_name":"Mariona Coll Ardanuy","orcid":"https://orcid.org/0000-0001-8455-7196"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mariona Coll Ardanuy","raw_affiliation_strings":["G\u00f6ttingen Centre for Digital Humanities, Heyne Haus, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"G\u00f6ttingen Centre for Digital Humanities, Heyne Haus, G\u00f6ttingen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010144873","display_name":"Caroline Sporleder","orcid":"https://orcid.org/0000-0002-5912-7028"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caroline Sporleder","raw_affiliation_strings":["G\u00f6ttingen Centre for Digital Humanities, Heyne Haus, G\u00f6ttingen, Germany"],"affiliations":[{"raw_affiliation_string":"G\u00f6ttingen Centre for Digital Humanities, Heyne Haus, G\u00f6ttingen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051763204"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.7799,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.97468959,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10757","display_name":"Geographic Information Systems Studies","score":0.993399977684021,"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":0.993399977684021,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9848999977111816,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9650999903678894,"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":0.8707111477851868},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6379486918449402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5948985815048218},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5766453146934509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5249944925308228},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4959789216518402},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.49590763449668884},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4636323153972626},{"id":"https://openalex.org/keywords/toponymy","display_name":"Toponymy","score":0.43708378076553345},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11080539226531982},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08043202757835388},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.07290336489677429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707111477851868},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6379486918449402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5948985815048218},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5766453146934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249944925308228},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4959789216518402},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.49590763449668884},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4636323153972626},{"id":"https://openalex.org/C116856471","wikidata":"https://www.wikidata.org/wiki/Q485762","display_name":"Toponymy","level":2,"score":0.43708378076553345},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11080539226531982},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08043202757835388},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.07290336489677429},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3078081.3078099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3078081.3078099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W86887328","https://openalex.org/W172861654","https://openalex.org/W1494366433","https://openalex.org/W1548663377","https://openalex.org/W1906503946","https://openalex.org/W1973312357","https://openalex.org/W1986353013","https://openalex.org/W2018277822","https://openalex.org/W2026810221","https://openalex.org/W2039955401","https://openalex.org/W2059128905","https://openalex.org/W2085337304","https://openalex.org/W2096765155","https://openalex.org/W2100341149","https://openalex.org/W2115352105","https://openalex.org/W2127289991","https://openalex.org/W2141835599","https://openalex.org/W2142889507","https://openalex.org/W2226371358","https://openalex.org/W2251896305","https://openalex.org/W2515960978"],"related_works":["https://openalex.org/W3172220373","https://openalex.org/W4223915615","https://openalex.org/W2958616596","https://openalex.org/W2181412350","https://openalex.org/W2737684396","https://openalex.org/W3125223822","https://openalex.org/W4220946479","https://openalex.org/W2378211422","https://openalex.org/W4310608224","https://openalex.org/W2232096346"],"abstract_inverted_index":{"Historians":[0],"are":[1,14,129],"often":[2],"interested":[3],"in":[4,8,33,46,54],"the":[5,75,99,102,111],"locations":[6,128],"mentioned":[7],"digitized":[9],"collections.":[10],"However,":[11],"place":[12],"names":[13],"highly":[15],"ambiguous":[16],"and":[17,50,62,84,97,109,120],"may":[18],"change":[19],"over":[20],"time,":[21],"which":[22],"makes":[23],"it":[24],"especially":[25],"hard":[26],"to":[27,36],"automatically":[28],"ground":[29],"mentions":[30],"of":[31,77,101,113],"places":[32],"historical":[34,93],"texts":[35],"their":[37,124],"real-world":[38],"referents.":[39],"Toponym":[40],"disambiguation":[41],"is":[42],"a":[43,70,92],"challenging":[44],"problem":[45],"natural":[47],"language":[48],"processing,":[49],"has":[51],"been":[52],"approached":[53],"two":[55,114],"different":[56],"yet":[57],"related":[58],"tasks:":[59],"toponym":[60,94],"resolution":[61,95],"entity":[63,117],"linking.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"weakly-supervised":[71],"method":[72,90],"that":[73],"combines":[74],"strengths":[76],"both":[78,82],"approaches":[79],"by":[80],"exploiting":[81],"geographic":[83],"semantic":[85],"features.":[86],"We":[87,104],"tested":[88,110],"our":[89],"against":[91],"benchmark":[96],"improved":[98,122],"state":[100],"art.":[103],"also":[105,121],"created":[106],"five":[107],"datasets":[108],"performance":[112,125],"state-of-the-art":[115],"out-of-the-box":[116],"linking":[118],"methods":[119],"on":[123],"when":[126],"only":[127],"considered.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
