{"id":"https://openalex.org/W2097106271","doi":"https://doi.org/10.1093/bioinformatics/btg1046","title":"Evaluation of text data mining for database curation:lessons learned from the KDD Challenge Cup","display_name":"Evaluation of text data mining for database curation:lessons learned from the KDD Challenge Cup","publication_year":2003,"publication_date":"2003-07-03","ids":{"openalex":"https://openalex.org/W2097106271","doi":"https://doi.org/10.1093/bioinformatics/btg1046","mag":"2097106271","pmid":"https://pubmed.ncbi.nlm.nih.gov/12855478"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg1046","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1046","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5109982569","display_name":"Alexander Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander S. Yeh","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068115280","display_name":"Lynette Hirschman","orcid":"https://orcid.org/0000-0001-8442-0720"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynette Hirschman","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108225476","display_name":"Alexander A. Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander A. Morgan","raw_affiliation_strings":["The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road, Bedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corporation, 202 Burlington Road,\nBedford, MA 01730, USA","institution_ids":["https://openalex.org/I44896327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":6.7594,"has_fulltext":false,"cited_by_count":175,"citation_normalized_percentile":{"value":0.97783118,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"19","issue":"suppl_1","first_page":"i331","last_page":"i339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9933000206947327,"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":0.9933000206947327,"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":0.9735999703407288,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9629999995231628,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7178016901016235},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.6231775879859924},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4844520092010498},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4571312665939331},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4555974006652832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4267970025539398},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4133654534816742},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3428686559200287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178016901016235},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.6231775879859924},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4844520092010498},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4571312665939331},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4555974006652832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4267970025539398},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4133654534816742},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3428686559200287},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000082","descriptor_name":"Acetaminophen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000082","descriptor_name":"Acetaminophen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000082","descriptor_name":"Acetaminophen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg1046","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1046","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:12855478","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12855478","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W107544894","https://openalex.org/W1490760466","https://openalex.org/W1939614505","https://openalex.org/W1956559956","https://openalex.org/W1958673034","https://openalex.org/W1980978505","https://openalex.org/W1988001261","https://openalex.org/W2004652662","https://openalex.org/W2017957082","https://openalex.org/W2056576456","https://openalex.org/W2122579798","https://openalex.org/W2135937947","https://openalex.org/W2146724934","https://openalex.org/W2152183901","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2701062589","https://openalex.org/W4308914582","https://openalex.org/W4388126069","https://openalex.org/W2567393658","https://openalex.org/W3200944274","https://openalex.org/W4306317641","https://openalex.org/W1488337274","https://openalex.org/W2216178707","https://openalex.org/W3095602079","https://openalex.org/W4287611188"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"biological":[2,11],"literature":[3,30],"is":[4],"a":[5,19,75,94,131],"major":[6],"repository":[7],"of":[8,15,22,29,34,53,97,101,112,133],"knowledge.":[9],"Many":[10],"databases":[12],"draw":[13],"much":[14],"their":[16],"content":[17],"from":[18,124],"careful":[20],"curation":[21,35,47],"this":[23],"literature.":[24],"However,":[25],"as":[26,117,119],"the":[27,32,46,51,83,109,120,127,138,152,164,169,173],"volume":[28],"increases,":[31],"burden":[33],"increases.":[36],"Text":[37],"mining":[38,63],"may":[39],"provide":[40],"useful":[41],"tools":[42],"to":[43,59,68],"assist":[44],"in":[45,105],"process.":[48],"To":[49],"date,":[50],"lack":[52],"standards":[54],"has":[55],"made":[56],"it":[57],"impossible":[58],"determine":[60],"whether":[61,151],"text":[62],"techniques":[64,170],"are":[65],"sufficiently":[66],"mature":[67],"be":[69],"useful.":[70],"RESULTS:":[71],"We":[72,92,161],"report":[73,162],"on":[74,150,163],"Challenge":[76,90],"Evaluation":[77],"task":[78],"that":[79,144],"we":[80,129],"created":[81],"for":[82,147,157],"Knowledge":[84],"Discovery":[85],"and":[86,114,167],"Data":[87],"Mining":[88],"(KDD)":[89],"Cup.":[91],"provided":[93,130,142],"training":[95],"corpus":[96,132],"862":[98],"articles":[99,103,146],"consisting":[100],"journal":[102],"curated":[104],"FlyBase,":[106],"along":[107],"with":[108],"associated":[110],"lists":[111],"genes":[113],"gene":[115,158],"products,":[116],"well":[118],"relevant":[121],"data":[122],"fields":[123],"FlyBase.":[125],"For":[126],"test,":[128],"213":[134],"new":[135],"('blind')":[136],"articles;":[137],"18":[139],"participating":[140],"groups":[141],"systems":[143],"flagged":[145],"curation,":[148],"based":[149],"article":[153],"contained":[154],"experimental":[155],"evidence":[156],"expression":[159],"products.":[160],"evaluation":[165],"results":[166],"describe":[168],"used":[171],"by":[172],"top":[174],"performing":[175],"groups.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":13}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
