{"id":"https://openalex.org/W4408403330","doi":"https://doi.org/10.1145/3677389.3702515","title":"Training a Geographic Entity Recognizer on Biomedical Abstracts with the Aid of Embeddings, Metadata, and Linked Data","display_name":"Training a Geographic Entity Recognizer on Biomedical Abstracts with the Aid of Embeddings, Metadata, and Linked Data","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4408403330","doi":"https://doi.org/10.1145/3677389.3702515"},"language":"en","primary_location":{"id":"doi:10.1145/3677389.3702515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055342020","display_name":"Xiaoliang Jiang","orcid":"https://orcid.org/0000-0002-9669-9041"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoliang Jiang","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-9669-9041","affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013490855","display_name":"Nigel Bosch","orcid":"https://orcid.org/0000-0003-2736-2899"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nigel Bosch","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-2736-2899","affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079566229","display_name":"Vetle I. Torvik","orcid":"https://orcid.org/0000-0002-0035-1850"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vetle I. Torvik","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0035-1850","affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9538000226020813,"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/T11937","display_name":"Research Data Management Practices","score":0.9035999774932861,"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/metadata","display_name":"Metadata","score":0.9331684112548828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766650915145874},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5166273713111877},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49352967739105225},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4929187297821045},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4072166681289673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34359315037727356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3084503412246704},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05430266261100769}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9331684112548828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766650915145874},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5166273713111877},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49352967739105225},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4929187297821045},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4072166681289673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34359315037727356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3084503412246704},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05430266261100769},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677389.3702515","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7003950339","display_name":null,"funder_award_id":"P01AG039347","funder_id":"https://openalex.org/F4320337337","funder_display_name":"National Institute on Aging"}],"funders":[{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W133073217","https://openalex.org/W1956471287","https://openalex.org/W1967400125","https://openalex.org/W1977116256","https://openalex.org/W2087518428","https://openalex.org/W2114920267","https://openalex.org/W2120545936","https://openalex.org/W2122496795","https://openalex.org/W2164466669","https://openalex.org/W2168041406","https://openalex.org/W2179272726","https://openalex.org/W2243423944","https://openalex.org/W2406908035","https://openalex.org/W2559948664","https://openalex.org/W2618851150","https://openalex.org/W2765563228","https://openalex.org/W2793058421","https://openalex.org/W2796495817","https://openalex.org/W2800130211","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2946119234","https://openalex.org/W2963625095","https://openalex.org/W2997394673","https://openalex.org/W3011573503","https://openalex.org/W3046832948","https://openalex.org/W3120336012","https://openalex.org/W3137481621","https://openalex.org/W3147959018","https://openalex.org/W3163259327","https://openalex.org/W3185956072","https://openalex.org/W3208515149","https://openalex.org/W4285160903","https://openalex.org/W4292083459","https://openalex.org/W4306680578","https://openalex.org/W4366078666","https://openalex.org/W4396624720","https://openalex.org/W6764970959"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Public":[0],"access":[1],"to":[2,40,57,102],"scientific":[3,98],"literature":[4],"has":[5],"fueled":[6],"research":[7],"in":[8,108],"text":[9],"mining":[10],"and":[11,44,54],"natural":[12],"language":[13],"processing,":[14],"yet":[15],"the":[16,86,104],"problem":[17],"of":[18,67,85,97,106],"geographic":[19],"named":[20],"entity":[21],"recognition":[22],"persists.":[23],"This":[24,90],"paper":[25],"describes":[26],"a":[27,46,63],"recognizer":[28],"that":[29,71],"uses":[30,45],"candidates":[31],"from":[32],"multiple":[33],"existing":[34],"Named":[35],"Entity":[36],"Recognition":[37],"(NER)":[38],"tools":[39],"ensure":[41],"high":[42,76],"recall":[43,77],"filtering":[47,73],"model":[48,74],"trained":[49],"on":[50,62],"sentence":[51],"embeddings,":[52],"metadata,":[53],"citation":[55],"data":[56],"improve":[58],"precision.":[59],"Experimental":[60],"results":[61],"manually":[64],"curated":[65],"set":[66],"biomedical":[68,109],"abstracts":[69],"show":[70],"this":[72],"preserves":[75],"while":[78],"achieving":[79],"much":[80],"higher":[81],"precision":[82],"than":[83],"all":[84],"individual":[87],"NER":[88],"tools.":[89],"should":[91],"enable":[92],"more":[93],"effective":[94],"geography-based":[95],"analysis":[96],"literature,":[99],"for":[100],"example,":[101],"study":[103],"role":[105],"place":[107],"discovery.":[110]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
