{"id":"https://openalex.org/W2057435879","doi":"https://doi.org/10.1109/bibm.2011.98","title":"Discriminative Application of String Similarity Methods to Chemical and Non-chemical Names for Biomedical Abbreviation Clustering","display_name":"Discriminative Application of String Similarity Methods to Chemical and Non-chemical Names for Biomedical Abbreviation Clustering","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2057435879","doi":"https://doi.org/10.1109/bibm.2011.98","mag":"2057435879"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2011.98","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2011.98","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Bioinformatics and Biomedicine","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/A5001958215","display_name":"Atsuko Yamaguchi","orcid":"https://orcid.org/0000-0001-7538-5337"},"institutions":[{"id":"https://openalex.org/I4210158934","display_name":"Research Organization of Information and Systems","ror":"https://ror.org/04p4e8t29","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Atsuko Yamaguchi","raw_affiliation_strings":["Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]},{"raw_affiliation_string":"Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063942302","display_name":"Yasunori Yamamoto","orcid":"https://orcid.org/0000-0002-6943-6887"},"institutions":[{"id":"https://openalex.org/I4210158934","display_name":"Research Organization of Information and Systems","ror":"https://ror.org/04p4e8t29","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasunori Yamamoto","raw_affiliation_strings":["Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]},{"raw_affiliation_string":"Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063923711","display_name":"Jin-Dong Kim","orcid":"https://orcid.org/0000-0001-9660-6303"},"institutions":[{"id":"https://openalex.org/I4210158934","display_name":"Research Organization of Information and Systems","ror":"https://ror.org/04p4e8t29","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jin-Dong Kim","raw_affiliation_strings":["Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]},{"raw_affiliation_string":"Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104355283","display_name":"Toshihisa Takagi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihisa Takagi","raw_affiliation_strings":["Department of Computational Biology, University of Tokyo, Kashiwa, Chiba, Japan","Dept. of Comput. Biol., Univ. of Tokyo, Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, University of Tokyo, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Dept. of Comput. Biol., Univ. of Tokyo, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109877761","display_name":"Akinori Yonezawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158934","display_name":"Research Organization of Information and Systems","ror":"https://ror.org/04p4e8t29","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Yonezawa","raw_affiliation_strings":["Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Database Center of Life Science, Research Organization of Information and Systems, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]},{"raw_affiliation_string":"Database Center for Life Sci., Res. Organ. of Inf. & Syst., Tokyo, Japan","institution_ids":["https://openalex.org/I4210158934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001958215"],"corresponding_institution_ids":["https://openalex.org/I4210158934"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09796559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"54","issue":null,"first_page":"544","last_page":"549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9668999910354614,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9627000093460083,"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/edit-distance","display_name":"Edit distance","score":0.724003255367279},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.688883900642395},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6809494495391846},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6805838346481323},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.658534824848175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.654273509979248},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6532759666442871},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.6234874725341797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5575662851333618},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5156213641166687},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46410903334617615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44911065697669983},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.4441743791103363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3523597717285156},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28061985969543457},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.2032189667224884},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1173279881477356},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08136436343193054}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.724003255367279},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.688883900642395},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6809494495391846},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6805838346481323},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.658534824848175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654273509979248},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6532759666442871},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.6234874725341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575662851333618},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5156213641166687},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46410903334617615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44911065697669983},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.4441743791103363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3523597717285156},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28061985969543457},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.2032189667224884},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1173279881477356},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08136436343193054},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2011.98","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2011.98","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W13703775","https://openalex.org/W1524134026","https://openalex.org/W1574901103","https://openalex.org/W1646278814","https://openalex.org/W1647671624","https://openalex.org/W1823786567","https://openalex.org/W1933390880","https://openalex.org/W1970026646","https://openalex.org/W1991154713","https://openalex.org/W2031627786","https://openalex.org/W2066102695","https://openalex.org/W2080018251","https://openalex.org/W2109252435","https://openalex.org/W2114420708","https://openalex.org/W2116040937","https://openalex.org/W2118658201","https://openalex.org/W2120609672","https://openalex.org/W2123269682","https://openalex.org/W2138807684","https://openalex.org/W2150698190","https://openalex.org/W2159583324","https://openalex.org/W3157207671","https://openalex.org/W6600552100","https://openalex.org/W6631223096","https://openalex.org/W6636771404","https://openalex.org/W6636915900","https://openalex.org/W6648116614","https://openalex.org/W6682056454"],"related_works":["https://openalex.org/W2950268498","https://openalex.org/W1505906253","https://openalex.org/W2102443632","https://openalex.org/W2461708070","https://openalex.org/W1982055477","https://openalex.org/W1815899388","https://openalex.org/W2061135126","https://openalex.org/W2463404432","https://openalex.org/W2162102353","https://openalex.org/W2612377428"],"abstract_inverted_index":{"Term":[0],"clustering":[1],"by":[2],"measuring":[3],"the":[4,18,41,51,56,59,64,81,102],"string":[5,36,52,85],"similarities":[6,53],"between":[7],"terms":[8],"is":[9],"known":[10],"to":[11,16,33,88,100],"be":[12,94],"an":[13],"effective":[14,98],"method":[15],"improve":[17,101],"quality":[19],"of":[20,84,104],"texts":[21],"and":[22,63,90],"dictionaries.":[23],"However,":[24],"based":[25],"on":[26],"our":[27],"observations,":[28],"chemical":[29,69,89],"names":[30,70,92],"are":[31],"difficult":[32],"cluster":[34],"using":[35,55],"similarity":[37,86],"measures":[38],"such":[39],"as":[40],"edit":[42,57],"distance.":[43],"To":[44],"demonstrate":[45],"this":[46],"difficulty":[47],"clearly,":[48],"we":[49],"compared":[50],"determined":[54],"distance,":[58],"Monge-Elkan":[60],"score,":[61],"SoftTFIDF,":[62],"bigram":[65],"Dice":[66],"coefficient":[67],"for":[68,73],"with":[71],"those":[72],"other":[74],"terms.":[75],"The":[76],"experimental":[77],"results":[78],"show":[79],"that":[80],"discriminative":[82],"application":[83],"methods":[87],"non-chemical":[91],"may":[93],"a":[95],"simple":[96],"but":[97],"way":[99],"performance":[103],"term":[105],"clustering.":[106]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}