{"id":"https://openalex.org/W2095017581","doi":"https://doi.org/10.1142/s0219720010004513","title":"THE VALUE OF AN IN-DOMAIN LEXICON IN GENOMICS QA","display_name":"THE VALUE OF AN IN-DOMAIN LEXICON IN GENOMICS QA","publication_year":2010,"publication_date":"2010-02-01","ids":{"openalex":"https://openalex.org/W2095017581","doi":"https://doi.org/10.1142/s0219720010004513","mag":"2095017581","pmid":"https://pubmed.ncbi.nlm.nih.gov/20183880"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720010004513","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720010004513","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5064752144","display_name":"Yutaka Sasaki","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":true,"raw_author_name":"YUTAKA SASAKI","raw_affiliation_strings":["National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom"],"affiliations":[{"raw_affiliation_string":"National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110478635","display_name":"John McNaught","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":"JOHN MCNAUGHT","raw_affiliation_strings":["National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom"],"affiliations":[{"raw_affiliation_string":"National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","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":["National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom"],"affiliations":[{"raw_affiliation_string":"National Centre for Text Mining, School of Computer Science, University of Manchester, MIB, 131 Princess Street, Manchester, M1 7DN, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064752144"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.793,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.71359746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"08","issue":"01","first_page":"147","last_page":"161"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T10028","display_name":"Topic Modeling","score":0.9912999868392944,"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/lexicon","display_name":"Lexicon","score":0.832988977432251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7188004851341248},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.7145346403121948},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5700789093971252},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.5522854924201965},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5504388809204102},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.540996789932251},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.43503478169441223},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43334463238716125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41929683089256287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3697947859764099},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33891403675079346},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13644066452980042},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.09485536813735962},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0713677704334259}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.832988977432251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188004851341248},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.7145346403121948},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5700789093971252},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.5522854924201965},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5504388809204102},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.540996789932251},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.43503478169441223},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43334463238716125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41929683089256287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3697947859764099},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33891403675079346},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13644066452980042},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.09485536813735962},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0713677704334259},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1142/s0219720010004513","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720010004513","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:20183880","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20183880","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 bioinformatics and computational biology","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/1f2e81a0-b85c-454f-af67-5cc5d62e0a3f","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/1f2e81a0-b85c-454f-af67-5cc5d62e0a3f","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":"Sasaki, Y, McNaught, J & Ananiadou, S 2010, 'The value of an in-domain lexicon in genomics QA', Journal of Bioinformatics and Computational Biology, vol. 8, no. 1, pp. 147-161. https://doi.org/10.1142/S0219720010004513","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/1f2e81a0-b85c-454f-af67-5cc5d62e0a3f","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/the-value-of-an-indomain-lexicon-in-genomics-qa(1f2e81a0-b85c-454f-af67-5cc5d62e0a3f).html","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sasaki, Y, McNaught, J & Ananiadou, S 2010, 'The value of an in-domain lexicon in genomics QA', Journal of Bioinformatics and Computational Biology, vol. 8, no. 1, pp. 147-161. https://doi.org/10.1142/S0219720010004513","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320291","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27"},{"id":"https://openalex.org/F4320320309","display_name":"Joint Information Systems Committee","ror":"https://ror.org/01rv9gx86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W80653726","https://openalex.org/W138519328","https://openalex.org/W184905683","https://openalex.org/W1507745332","https://openalex.org/W1829379010","https://openalex.org/W1994306321","https://openalex.org/W2038721957","https://openalex.org/W2086511124","https://openalex.org/W2127241285","https://openalex.org/W2228162160","https://openalex.org/W2586259647","https://openalex.org/W4235505822"],"related_works":["https://openalex.org/W1979345825","https://openalex.org/W2748907937","https://openalex.org/W857360071","https://openalex.org/W331900753","https://openalex.org/W2574577419","https://openalex.org/W2028102159","https://openalex.org/W17897903","https://openalex.org/W2968649782","https://openalex.org/W96790119","https://openalex.org/W2417906941"],"abstract_inverted_index":{"This":[0],"paper":[1],"demonstrates":[2],"that":[3,149,159],"a":[4,54,77,129],"large-scale":[5],"lexicon":[6,88],"tailored":[7],"for":[8,18,135,138],"the":[9,25,32,80,143,153,163],"biology":[10],"domain":[11],"is":[12,40,123,133],"effective":[13,134],"in":[14,46,49,63,83],"improving":[15],"question":[16,36,136,150],"analysis":[17,37,151],"genomics":[19,111,139,144],"Question":[20],"Answering":[21],"(QA).":[22],"We":[23],"use":[24],"TREC":[26],"Genomics":[27],"Track":[28],"data":[29,146],"to":[30,42,53,126],"evaluate":[31],"performance":[33],"of":[34,57,98],"different":[35],"methods.":[38],"It":[39],"hard":[41],"process":[43],"textual":[44],"information":[45],"biology,":[47,51],"especially":[48],"molecular":[50],"due":[52],"huge":[55],"number":[56],"technical":[58],"terms":[59,96,101,103],"which":[60],"rarely":[61],"appear":[62],"general":[64],"English":[65],"documents":[66],"and":[67,102,120,162],"dictionaries.":[68],"To":[69],"support":[70],"biological":[71],"Text":[72],"Mining,":[73],"we":[74],"have":[75],"developed":[76],"domain-specific":[78],"resource,":[79],"BioLexicon.":[81],"Started":[82],"2006":[84],"from":[85,105],"scratch,":[86],"this":[87],"currently":[89],"includes":[90],"more":[91],"than":[92,158],"four":[93],"million":[94],"biomedical":[95,107],"consisting":[97],"newly":[99],"curated":[100],"collected":[104],"existing":[106],"databases.":[108],"While":[109],"conventional":[110],"QA":[112,145],"systems":[113],"provide":[114],"query":[115],"expansion":[116],"based":[117],"on":[118,142],"thesauri":[119],"dictionaries,":[121],"it":[122],"not":[124],"clear":[125],"what":[127],"extent":[128],"biology-oriented":[130],"lexical":[131],"resource":[132],"pre-processing":[137],"QA.":[140],"Experiments":[141],"set":[147],"show":[148],"using":[152,160],"BioLexicon":[154],"performs":[155],"slightly":[156],"better":[157],"n-grams":[161],"UMLS":[164],"Specialist":[165],"Lexicon.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}