{"id":"https://openalex.org/W2132679456","doi":"https://doi.org/10.1186/2041-1480-5-26","title":"Generalising semantic category disambiguation with large lexical resources for fun and profit","display_name":"Generalising semantic category disambiguation with large lexical resources for fun and profit","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2132679456","doi":"https://doi.org/10.1186/2041-1480-5-26","mag":"2132679456","pmid":"https://pubmed.ncbi.nlm.nih.gov/25093067"},"language":"en","primary_location":{"id":"doi:10.1186/2041-1480-5-26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-5-26","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-5-26","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-5-26","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049427071","display_name":"Pontus Stenetorp","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":true,"raw_author_name":"Pontus Stenetorp","raw_affiliation_strings":["Department of Computer Science, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066925770","display_name":"Sampo Pyysalo","orcid":"https://orcid.org/0000-0002-6279-5000"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sampo Pyysalo","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK","School of Computer Science, University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077976343","display_name":"Sophia Ananiadou","orcid":"https://orcid.org/0000-0002-4097-9191"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sophia Ananiadou","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK","School of Computer Science, University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112241147","display_name":"Jun\u2019ichi Tsujii","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun\u2019ichi Tsujii","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK ; Microsoft Research Asia, Beijing, People's Republic of China","National Centre for Text Mining, University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK ; National Centre for Text Mining, University of Manchester, Manchester, UK ; Microsoft Research Asia, Beijing, People's Republic of China","institution_ids":[]},{"raw_affiliation_string":"National Centre for Text Mining, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049427071"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":1190,"currency":"GBP","value_usd":1459},"apc_paid":{"value":1190,"currency":"GBP","value_usd":1459},"fwci":0.8284,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81875178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":"1","first_page":"26","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4675000011920929,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.4675000011920929,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.4262999892234802,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.01769999973475933,"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":0.8701287508010864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6331509351730347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5356559157371521},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5071334838867188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701287508010864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6331509351730347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5356559157371521},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5071334838867188}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/2041-1480-5-26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-5-26","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-5-26","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmid:25093067","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25093067","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":"Journal of biomedical semantics","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/412f4138-eb18-4fe3-9f57-b3f64635ebba","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/412f4138-eb18-4fe3-9f57-b3f64635ebba","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Stenetorp, P, Pyysalo, S, Ananiadou, S & Tsujii, J 2014, 'Generalising semantic category disambiguation with large lexical resources for fun and profit', Journal of Biomedical Semantics, vol. 5. https://doi.org/10.1186/2041-1480-5-26","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:europepmc.org:3089630","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4107982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pure.atira.dk:publications/412f4138-eb18-4fe3-9f57-b3f64635ebba","is_oa":true,"landing_page_url":"http://www.jbiomedsem.com/content/5/1/26/abstract","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"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":"Stenetorp, P, Pyysalo, S, Ananiadou, S & Tsujii, J 2014, 'Generalising semantic category disambiguation with large lexical resources for fun and profit', Journal of Biomedical Semantics, vol. 5. https://doi.org/10.1186/2041-1480-5-26","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/2041-1480-5-26","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-5-26","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-5-26","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320320936","display_name":"Royal Swedish Academy of Sciences","ror":"https://ror.org/00j62qv07"},{"id":"https://openalex.org/F4320323700","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2132679456.pdf","grobid_xml":"https://content.openalex.org/works/W2132679456.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W8550301","https://openalex.org/W49621856","https://openalex.org/W97427318","https://openalex.org/W107258648","https://openalex.org/W142292357","https://openalex.org/W154351976","https://openalex.org/W174568167","https://openalex.org/W1502957213","https://openalex.org/W1510579866","https://openalex.org/W1529842856","https://openalex.org/W1630427015","https://openalex.org/W1659833910","https://openalex.org/W1786456657","https://openalex.org/W1850865022","https://openalex.org/W1984314602","https://openalex.org/W2001804590","https://openalex.org/W2004763266","https://openalex.org/W2005058680","https://openalex.org/W2006517287","https://openalex.org/W2047782770","https://openalex.org/W2056616115","https://openalex.org/W2074640468","https://openalex.org/W2098722636","https://openalex.org/W2100627415","https://openalex.org/W2101819947","https://openalex.org/W2103017472","https://openalex.org/W2107580398","https://openalex.org/W2107598941","https://openalex.org/W2110279753","https://openalex.org/W2114039834","https://openalex.org/W2118585731","https://openalex.org/W2121244856","https://openalex.org/W2123241698","https://openalex.org/W2124214517","https://openalex.org/W2131887446","https://openalex.org/W2131924932","https://openalex.org/W2144578941","https://openalex.org/W2144789800","https://openalex.org/W2153848201","https://openalex.org/W2159583324","https://openalex.org/W2314759160","https://openalex.org/W2529518929","https://openalex.org/W2588245530","https://openalex.org/W2911759240","https://openalex.org/W2914431807","https://openalex.org/W2915429162","https://openalex.org/W2952087486","https://openalex.org/W2968573267","https://openalex.org/W4302064534","https://openalex.org/W4302583945","https://openalex.org/W4320800138","https://openalex.org/W6759374832"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"BACKGROUND:":[0],"Semantic":[1],"Category":[2],"Disambiguation":[3],"(SCD)":[4],"is":[5,32,243,290],"the":[6,10,78,86,91,139,195,217,246,275,285],"task":[7,125],"of":[8,17,23,80,88,93,141,197,213,219,250,260,277],"assigning":[9],"appropriate":[11,205,267],"semantic":[12,131,198,221],"category":[13],"to":[14,29,34,67,73,133,137,202,245,256,292,295],"given":[15,266],"spans":[16],"text":[18,261,307],"from":[19,200],"a":[20,100,119,124,159,174,257,303],"fixed":[21],"set":[22],"candidate":[24,220,278],"categories,":[25],"for":[26,90,103,129,157,320],"example":[27],"Protein":[28],"\"Fibrin\".":[30],"SCD":[31,56,89,116,170,234],"relevant":[33],"Natural":[35,105],"Language":[36,106],"Processing":[37,107],"tasks":[38,299],"such":[39],"as":[40,99,118,302],"Named":[41],"Entity":[42],"Recognition,":[43],"coreference":[44],"resolution":[45],"and":[46,62,77,97,162,180,189,192,239,248,263,269,300,313],"coordination":[47],"resolution.":[48],"In":[49],"this":[50,150],"work,":[51],"we":[52,122],"study":[53],"machine":[54,177],"learning-based":[55,178,233],"methods":[57,70],"using":[58,235],"large":[59,236],"lexical":[60,75,237,251],"resources":[61,76,238,268,316],"approximate":[63,240],"string":[64,241],"matching,":[65],"aiming":[66,136],"generalise":[68],"these":[69],"with":[71],"regard":[72],"domains,":[74],"composition":[79],"data":[81,229,264],"sets.":[82,230],"We":[83,147,167],"specifically":[84],"consider":[85,123],"applicability":[87],"purposes":[92,322],"supporting":[94,164],"human":[95,165],"annotators":[96],"acting":[98],"pipeline":[101,160],"component":[102,161,305],"other":[104],"systems.":[108],"RESULTS:":[109],"While":[110],"previous":[111],"research":[112,321],"has":[113],"mostly":[114],"cast":[115],"purely":[117],"classification":[120],"task,":[121],"setting":[126,151],"that":[127,149],"allows":[128],"multiple":[130],"categories":[132,199,222,279],"be":[134,293],"suggested,":[135],"minimise":[138],"number":[140,196,218,276],"suggestions":[142],"while":[143,215,280],"maintaining":[144],"high":[145],"recall.":[146],"argue":[148],"reflects":[152],"aspects":[153],"which":[154],"are":[155,317],"essential":[156],"both":[158],"when":[163],"annotators.":[166],"introduce":[168],"an":[169,210],"method":[171,289],"based":[172],"on":[173,183,223],"recently":[175],"introduced":[176,311],"system":[179,208,312],"evaluate":[181],"it":[182],"15":[184],"corpora":[185],"covering":[186],"biomedical,":[187],"clinical":[188],"newswire":[190],"texts":[191],"ranging":[193],"in":[194,306],"2":[201],"91.":[203],"With":[204],"settings,":[206],"our":[207,288],"maintains":[209],"average":[211,224],"recall":[212],"99%":[214],"reducing":[216,274],"by":[225],"65%":[226],"over":[227],"all":[228,314],"CONCLUSIONS:":[231],"Machine":[232],"matching":[242],"sensitive":[244],"selection":[247],"granularity":[249],"resources,":[252],"but":[253],"generalises":[254],"well":[255],"wide":[258],"range":[259],"domains":[262],"sets":[265],"parameter":[270],"settings.":[271],"By":[272],"substantially":[273],"only":[281],"very":[282],"rarely":[283],"excluding":[284],"correct":[286],"one,":[287],"shown":[291],"applicable":[294],"manual":[296],"annotation":[297],"support":[298],"use":[301],"high-recall":[304],"processing":[308],"pipelines.":[309],"The":[310],"related":[315],"freely":[318],"available":[319],"at:":[323],"https://github.com/ninjin/simsem.":[324]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}