{"id":"https://openalex.org/W1987213598","doi":"https://doi.org/10.3115/1118958.1118974","title":"Selecting text features for gene name classification","display_name":"Selecting text features for gene name classification","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1987213598","doi":"https://doi.org/10.3115/1118958.1118974","mag":"1987213598"},"language":"en","primary_location":{"id":"doi:10.3115/1118958.1118974","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118974","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118974","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goran Nenadi\u0107","raw_affiliation_strings":["UMIST, Manchester","UMIST-Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMIST, Manchester","institution_ids":[]},{"raw_affiliation_string":"UMIST-Manchester","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073899463","display_name":"Simon Rice","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Rice","raw_affiliation_strings":["UMIST, Manchester","UMIST-Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMIST, Manchester","institution_ids":[]},{"raw_affiliation_string":"UMIST-Manchester","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016345745","display_name":"\u202aIrena Spasi\u0107","orcid":"https://orcid.org/0000-0002-8132-3885"},"institutions":[{"id":"https://openalex.org/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Irena Spasi\u0107","raw_affiliation_strings":["University of Salford, Salford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Salford, Salford","institution_ids":["https://openalex.org/I54459138"]}]},{"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/I54459138","display_name":"University of Salford","ror":"https://ror.org/01tmqtf75","country_code":"GB","type":"education","lineage":["https://openalex.org/I54459138"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sophia Ananiadou","raw_affiliation_strings":["University of Salford, Salford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Salford, Salford","institution_ids":["https://openalex.org/I54459138"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086617519","display_name":"Benjamin J. Stapley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Stapley","raw_affiliation_strings":["UMIST, Manchester","UMIST-Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMIST, Manchester","institution_ids":[]},{"raw_affiliation_string":"UMIST-Manchester","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3748,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.79066222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"13","issue":null,"first_page":"121","last_page":"128"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9901000261306763,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9886000156402588,"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":0.7221238017082214},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5932431817054749},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5521692633628845},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49187493324279785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49087435007095337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4477262794971466},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4423591196537018},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44038864970207214},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.4364981949329376},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43202993273735046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1322135627269745},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11929705739021301},{"id":"https://openalex.org/keywords/nomenclature","display_name":"Nomenclature","score":0.08626091480255127},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.08478495478630066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7221238017082214},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5932431817054749},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5521692633628845},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49187493324279785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49087435007095337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4477262794971466},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4423591196537018},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44038864970207214},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.4364981949329376},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43202993273735046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1322135627269745},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11929705739021301},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.08626091480255127},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.08478495478630066},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1118958.1118974","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118974","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1118958.1118974","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118974","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118974","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1987213598.pdf","grobid_xml":"https://content.openalex.org/works/W1987213598.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1493036841","https://openalex.org/W1564518192","https://openalex.org/W1780090776","https://openalex.org/W1967488025","https://openalex.org/W1981933378","https://openalex.org/W1999117234","https://openalex.org/W1999208044","https://openalex.org/W2049107599","https://openalex.org/W2093723065","https://openalex.org/W2094560491","https://openalex.org/W2098162425","https://openalex.org/W2103017472","https://openalex.org/W2106093878","https://openalex.org/W2107425660","https://openalex.org/W2114535528","https://openalex.org/W2118591827","https://openalex.org/W2124861498","https://openalex.org/W2127675721","https://openalex.org/W2134769633","https://openalex.org/W2149684865","https://openalex.org/W2151598682","https://openalex.org/W2156909104","https://openalex.org/W2159203162","https://openalex.org/W2162461580","https://openalex.org/W2463773143","https://openalex.org/W4285719527","https://openalex.org/W4388861687"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W1515070932","https://openalex.org/W2090763504","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"discuss":[4],"the":[5,20,27,83,87],"performance":[6,84],"of":[7,16,23,52,65],"a":[8,33,63],"text-based":[9],"classification":[10,22],"approach":[11],"by":[12,31],"comparing":[13],"different":[14],"types":[15],"features.":[17],"We":[18],"consider":[19],"automatic":[21],"gene":[24,69],"names":[25,70],"from":[26,40],"molecular":[28],"biology":[29],"literature,":[30],"using":[32,78],"support-vector":[34],"machine":[35],"method.":[36],"Classification":[37],"features":[38],"range":[39],"words,":[41],"lemmas":[42],"and":[43,71,99],"stems,":[44],"to":[45,86],"automatically":[46],"extracted":[47],"terms.":[48],"Also,":[49],"simple":[50],"co-occurrences":[51],"genes":[53,94],"within":[54],"documents":[55],"are":[56],"considered.":[57],"The":[58],"preliminary":[59],"experiments":[60],"performed":[61],"on":[62],"set":[64],"3,000":[66],"S.":[67],"cerevisiae":[68],"53,000":[72],"Medline":[73],"abstracts":[74],"have":[75],"shown":[76],"that":[77],"domain-specific":[79],"terms":[80],"can":[81],"improve":[82],"compared":[85],"standard":[88],"bag-of-words":[89],"approach,":[90],"in":[91],"particular":[92],"for":[93,100],"classified":[95],"with":[96],"higher":[97],"confidence,":[98],"under-represented":[101],"classes.":[102]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}