{"id":"https://openalex.org/W4401103265","doi":"https://doi.org/10.1093/database/baae067","title":"Improving biomedical entity linking for complex entity mentions with LLM-based text simplification","display_name":"Improving biomedical entity linking for complex entity mentions with LLM-based text simplification","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401103265","doi":"https://doi.org/10.1093/database/baae067","pmid":"https://pubmed.ncbi.nlm.nih.gov/39066514"},"language":"en","primary_location":{"id":"doi:10.1093/database/baae067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae067/58662801/baae067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae067/58662801/baae067.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006643663","display_name":"Florian Borchert","orcid":"https://orcid.org/0000-0003-1079-6500"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Florian Borchert","raw_affiliation_strings":["Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1079-6500","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077519770","display_name":"Ignacio Llorca","orcid":"https://orcid.org/0009-0005-6256-1879"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ignacio Llorca","raw_affiliation_strings":["Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053012847","display_name":"Matthieu-P. Schapranow","orcid":"https://orcid.org/0000-0001-6601-2942"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]},{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthieu-P Schapranow","raw_affiliation_strings":["Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6601-2942","affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute for Digital Engineering, University of Potsdam , Prof.-Dr.-Helmert-Stra\u00dfe 2-3, Potsdam 14482, Germany","institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006643663"],"corresponding_institution_ids":["https://openalex.org/I143288331","https://openalex.org/I176453806"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":2.1003,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87610881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"2024","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9947999715805054,"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":0.7283205389976501},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5970075726509094},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.46908894181251526},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46492457389831543},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3560243546962738},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.07147350907325745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283205389976501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5970075726509094},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.46908894181251526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46492457389831543},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3560243546962738},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.07147350907325745}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/baae067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae067/58662801/baae067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:39066514","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39066514","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11281847","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11281847","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11281847/pdf/baae067.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baae067","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae067","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae067/58662801/baae067.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401103265.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1747666062","https://openalex.org/W2002514548","https://openalex.org/W2159583324","https://openalex.org/W2404369708","https://openalex.org/W2576491980","https://openalex.org/W2801213160","https://openalex.org/W2912971066","https://openalex.org/W3014809049","https://openalex.org/W3032553678","https://openalex.org/W3035390927","https://openalex.org/W3046375318","https://openalex.org/W3104748221","https://openalex.org/W3164540570","https://openalex.org/W4200196700","https://openalex.org/W4223546521","https://openalex.org/W4283773284","https://openalex.org/W4285116174","https://openalex.org/W4287889463","https://openalex.org/W4311903220","https://openalex.org/W4381587418","https://openalex.org/W4389518747","https://openalex.org/W4389519296","https://openalex.org/W4391973028","https://openalex.org/W4394637965","https://openalex.org/W6713634263","https://openalex.org/W6751601522","https://openalex.org/W6759960650","https://openalex.org/W6769263558","https://openalex.org/W6783763837","https://openalex.org/W6784131931","https://openalex.org/W6810226671","https://openalex.org/W6838616034","https://openalex.org/W6840160128","https://openalex.org/W6840891171","https://openalex.org/W6845943790","https://openalex.org/W6856771802","https://openalex.org/W6858981608","https://openalex.org/W6859932045","https://openalex.org/W6911304643","https://openalex.org/W6948729738","https://openalex.org/W6967751204"],"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/W2485077425","https://openalex.org/W4390279576","https://openalex.org/W2098057544"],"abstract_inverted_index":{"Large":[0],"amounts":[1],"of":[2,43,49,63,83,118,124,129,208,219],"important":[3],"medical":[4,50],"information":[5],"are":[6,74,158],"captured":[7],"in":[8,11,31,106,121,154,184,196],"free-text":[9],"documents":[10],"biomedical":[12,33],"research":[13],"and":[14],"within":[15],"healthcare":[16],"systems,":[17],"which":[18,179,237],"can":[19,164,198],"be":[20,199],"made":[21],"accessible":[22],"through":[23,205],"natural":[24],"language":[25,112],"processing":[26],"(NLP).":[27],"A":[28],"key":[29],"component":[30],"most":[32],"NLP":[34],"pipelines":[35],"is":[36,238],"entity":[37,69,126],"linking,":[38],"i.e.":[39],"grounding":[40],"textual":[41],"mentions":[42,98],"named":[44],"entities":[45],"to":[46,77,80,95,160,175],"a":[47,55,147,209],"reference":[48],"concepts,":[51],"usually":[52],"derived":[53],"from":[54],"terminology":[56],"system,":[57,178],"such":[58,97],"as":[59],"the":[60,81,116,122,125,130,140,181,185,222,233],"Systematized":[61],"Nomenclature":[62],"Medicine":[64],"Clinical":[65],"Terms.":[66],"However,":[67],"complex":[68],"mentions,":[70],"spanning":[71],"multiple":[72],"tokens,":[73],"notoriously":[75],"hard":[76],"normalize":[78],"due":[79],"difficulty":[82],"finding":[84],"appropriate":[85],"candidate":[86,100,168],"concepts.":[87],"In":[88],"this":[89,194],"work,":[90],"we":[91,163,191],"propose":[92],"an":[93,217],"approach":[94,228],"preprocess":[96],"for":[99,150],"generation,":[101],"building":[102],"upon":[103],"recent":[104],"advances":[105],"text":[107,151],"simplification":[108,152],"with":[109,146],"generative":[110],"large":[111],"models.":[113],"We":[114,136],"evaluate":[115],"feasibility":[117],"our":[119,176],"method":[120],"context":[123],"linking":[127],"track":[128],"BioCreative":[131],"VIII":[132],"SympTEMIST":[133,223],"shared":[134,187],"task.":[135],"find":[137],"that":[138,157,193],"instructing":[139],"latest":[141],"Generative":[142],"Pre-trained":[143],"Transformer":[144],"model":[145],"few-shot":[148],"prompt":[149],"results":[153],"mention":[155],"spans":[156],"easier":[159],"normalize.":[161],"Thus,":[162],"improve":[165],"recall":[166,197],"during":[167],"generation":[169],"by":[170],"2.9":[171],"percentage":[172],"points":[173],"compared":[174],"baseline":[177],"achieved":[180],"best":[182,214],"score":[183],"original":[186],"task":[188],"evaluation.":[189],"Furthermore,":[190],"show":[192],"improvement":[195],"fully":[200],"translated":[201],"into":[202,232],"top-1":[203],"accuracy":[204,218],"careful":[206],"initialization":[207],"subsequent":[210],"reranking":[211],"model.":[212],"Our":[213],"system":[215],"achieves":[216],"63.6%":[220],"on":[221],"test":[224],"set.":[225],"The":[226],"proposed":[227],"has":[229],"been":[230],"integrated":[231],"open-source":[234],"xMEN":[235],"toolkit,":[236],"available":[239],"online":[240],"via":[241],"https://github.com/hpi-dhc/xmen.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}