{"id":"https://openalex.org/W4205826620","doi":"https://doi.org/10.1109/bibm52615.2021.9669475","title":"Data Normalization Improves Semantic Annotation \u2013 a Case Study of Rare Disease Name Annotation","display_name":"Data Normalization Improves Semantic Annotation \u2013 a Case Study of Rare Disease Name Annotation","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4205826620","doi":"https://doi.org/10.1109/bibm52615.2021.9669475","pmid":"https://pubmed.ncbi.nlm.nih.gov/40932881"},"language":"en","primary_location":{"id":"doi:10.1109/bibm52615.2021.9669475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669475","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12419296/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009775597","display_name":"Charlie Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I919803642","display_name":"American Axle & Manufacturing (United States)","ror":"https://ror.org/00atq5220","country_code":"US","type":"company","lineage":["https://openalex.org/I919803642"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charlie Tang","raw_affiliation_strings":["Axle Informatics, LLC, Rockville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Axle Informatics, LLC, Rockville, USA","institution_ids":["https://openalex.org/I919803642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004924663","display_name":"Yanji Xu","orcid":"https://orcid.org/0000-0001-8033-3793"},"institutions":[{"id":"https://openalex.org/I4210148682","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210148682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanji Xu","raw_affiliation_strings":["Office of Rare Disease Research, National Center for Advancing Translational Sciences, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office of Rare Disease Research, National Center for Advancing Translational Sciences, Bethesda, USA","institution_ids":["https://openalex.org/I4210148682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073074181","display_name":"Qian Zhu","orcid":"https://orcid.org/0000-0002-4858-6333"},"institutions":[{"id":"https://openalex.org/I4210148682","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210148682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Zhu","raw_affiliation_strings":["Division of Pre-Clinical Innovation, National Center for Advancing Translational Sciences, Rockville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Pre-Clinical Innovation, National Center for Advancing Translational Sciences, Rockville, USA","institution_ids":["https://openalex.org/I4210148682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0813,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87057728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2021","issue":null,"first_page":"2609","last_page":"2611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.9674999713897705,"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/annotation","display_name":"Annotation","score":0.9362494945526123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299207448959351},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6524096727371216},{"id":"https://openalex.org/keywords/temporal-annotation","display_name":"Temporal annotation","score":0.5038406252861023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4791416525840759},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45523738861083984},{"id":"https://openalex.org/keywords/informatics","display_name":"Informatics","score":0.4455450773239136},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4208534061908722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4179237186908722},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27366310358047485},{"id":"https://openalex.org/keywords/language-technology","display_name":"Language technology","score":0.07658752799034119}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.9362494945526123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299207448959351},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6524096727371216},{"id":"https://openalex.org/C7044111","wikidata":"https://www.wikidata.org/wiki/Q15844891","display_name":"Temporal annotation","level":5,"score":0.5038406252861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4791416525840759},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45523738861083984},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.4455450773239136},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4208534061908722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4179237186908722},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27366310358047485},{"id":"https://openalex.org/C14919245","wikidata":"https://www.wikidata.org/wiki/Q1976109","display_name":"Language technology","level":4,"score":0.07658752799034119},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bibm52615.2021.9669475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669475","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmid:40932881","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40932881","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":"Proceedings. IEEE International Conference on Bioinformatics and Biomedicine","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12419296","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12419296/","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings (IEEE Int Conf Bioinformatics Biomed)","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12419296","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12419296/","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings (IEEE Int Conf Bioinformatics Biomed)","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1550258693","https://openalex.org/W2169099542","https://openalex.org/W2760618582","https://openalex.org/W3103412787","https://openalex.org/W3212232262","https://openalex.org/W6632766574"],"related_works":["https://openalex.org/W4377865234","https://openalex.org/W2080575979","https://openalex.org/W2793132289","https://openalex.org/W4385569300","https://openalex.org/W48671780","https://openalex.org/W1994489417","https://openalex.org/W2369337446","https://openalex.org/W2573587940","https://openalex.org/W2061851981","https://openalex.org/W3145920652"],"abstract_inverted_index":{"Despite":[0],"the":[1,47],"individually":[2],"low":[3],"prevalence":[4],"of":[5,19],"rare":[6,20],"diseases,":[7],"they":[8],"collectively":[9],"constitute":[10],"a":[11,40],"big":[12],"challenge":[13],"to":[14,46],"human":[15],"health.":[16],"Accurate":[17],"annotation":[18,43,51,57],"diseases":[21],"in":[22,33,61],"biomedical":[23,34,49,59],"data":[24,41,50,60],"through":[25],"natural":[26],"language":[27],"processing":[28],"(NLP)":[29],"could":[30],"be":[31],"instrumental":[32],"informatics":[35],"research.":[36],"Herein,":[37],"we":[38],"propose":[39],"normalization-based":[42],"approach,":[44],"complementary":[45],"popular":[48],"tool":[52],"named":[53],"MetaMap,":[54],"for":[55],"disease":[56],"from":[58],"free":[62],"text.":[63]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
