{"id":"https://openalex.org/W2160805010","doi":"https://doi.org/10.1186/1471-2105-13-17","title":"Training text chunkers on a silver standard corpus: can silver replace gold?","display_name":"Training text chunkers on a silver standard corpus: can silver replace gold?","publication_year":2012,"publication_date":"2012-01-30","ids":{"openalex":"https://openalex.org/W2160805010","doi":"https://doi.org/10.1186/1471-2105-13-17","mag":"2160805010","pmid":"https://pubmed.ncbi.nlm.nih.gov/22289351"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-17","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-17","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-17","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076346443","display_name":"Kang Ning","orcid":"https://orcid.org/0000-0003-3325-5387"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ning Kang","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, P,O, Box 2040, 3000 CA Rotterdam, The Netherlands. n.kang@erasmusmc.nl","Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, P,O, Box 2040, 3000 CA Rotterdam, The Netherlands. n.kang@erasmusmc.nl","institution_ids":["https://openalex.org/I2801952686"]},{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053857782","display_name":"Erik M. van Mulligen","orcid":"https://orcid.org/0000-0003-1377-9386"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Erik M van Mulligen","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005077862","display_name":"Jan A. Kors","orcid":"https://orcid.org/0000-0002-4929-026X"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"healthcare","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jan A Kors","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, P.O. Box 2040, 3000, CA, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076346443"],"corresponding_institution_ids":["https://openalex.org/I2801952686"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.9818,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.74479364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"1","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.3995000123977661,"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":0.3995000123977661,"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":0.17270000278949738,"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":0.15029999613761902,"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/noun-phrase","display_name":"Noun phrase","score":0.7812639474868774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7812118530273438},{"id":"https://openalex.org/keywords/chunking","display_name":"Chunking (psychology)","score":0.6959090828895569},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6280146837234497},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.61094069480896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6045405268669128},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5581045150756836},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5388125777244568},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5314838886260986},{"id":"https://openalex.org/keywords/gold-standard","display_name":"Gold standard (test)","score":0.5125236511230469},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.44824936985969543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09915712475776672}],"concepts":[{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.7812639474868774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812118530273438},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.6959090828895569},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6280146837234497},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.61094069480896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6045405268669128},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5581045150756836},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5388125777244568},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5314838886260986},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.5125236511230469},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.44824936985969543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09915712475776672},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","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}],"locations_count":7,"locations":[{"id":"doi:10.1186/1471-2105-13-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-17","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-17","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22289351","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22289351","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pure.eur.nl:openaire/3336477e-001c-44d3-9d7a-311407568c81","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/3336477e-001c-44d3-9d7a-311407568c81","pdf_url":"https://pure.eur.nl/ws/files/47466256/1123.pdf","source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Kang, N, van Mulligen, E & Kors, J 2012, 'Training text chunkers on a silver standard corpus: can silver replace gold?', BMC Bioinformatics, vol. 13. https://doi.org/10.1186/1471-2105-13-17","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:eur:oai:repub.eur.nl:38312","is_oa":true,"landing_page_url":"http://hdl.handle.net/1765/38312","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"B M C Bioinformatics, 13(1)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:fa7d57cff7074eb39ea5dbef0bfc8059","is_oa":true,"landing_page_url":"https://doaj.org/article/fa7d57cff7074eb39ea5dbef0bfc8059","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss 1, p 17 (2012)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3280170","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3280170","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:repub.eur.nl:38312","is_oa":true,"landing_page_url":"http://repub.eur.nl/pub/38312","pdf_url":null,"source":{"id":"https://openalex.org/S4377196287","display_name":"RePub (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"B M C Bioinformatics vol. 13 no. 1","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-17","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-17","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-17","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1876684263","display_name":"Collaborative Annotation of a Large Biomedical Corpus","funder_award_id":"231727","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5593277320","display_name":null,"funder_award_id":"2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160805010.pdf","grobid_xml":"https://content.openalex.org/works/W2160805010.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W102233799","https://openalex.org/W124954147","https://openalex.org/W1545305210","https://openalex.org/W1550258693","https://openalex.org/W1607983314","https://openalex.org/W1988995507","https://openalex.org/W2025365931","https://openalex.org/W2032566933","https://openalex.org/W2062331696","https://openalex.org/W2068017609","https://openalex.org/W2093825590","https://openalex.org/W2094618127","https://openalex.org/W2096797897","https://openalex.org/W2098921539","https://openalex.org/W2105324886","https://openalex.org/W2116159459","https://openalex.org/W2154142897","https://openalex.org/W2159845109","https://openalex.org/W2167917621","https://openalex.org/W2604664386","https://openalex.org/W2773439987"],"related_works":["https://openalex.org/W2384729545","https://openalex.org/W2198395236","https://openalex.org/W2800417007","https://openalex.org/W147604216","https://openalex.org/W2025590371","https://openalex.org/W2122100102","https://openalex.org/W4236833069","https://openalex.org/W2135991045","https://openalex.org/W2033585854","https://openalex.org/W3102012802"],"abstract_inverted_index":{"BACKGROUND:":[0],"To":[1],"train":[2],"chunkers":[3,77,98,197,246,283,311],"in":[4,11,75,83,96,149,157,168,185,312,339],"recognizing":[5],"noun":[6],"phrases":[7,10],"and":[8,29,37,94,124,126,131,171],"verb":[9],"biomedical":[12,314],"text,":[13],"an":[14,81,102,110,222,258,295],"annotated":[15],"corpus":[16,55],"is":[17,27,58,91,325,334],"required.":[18],"The":[19,272],"creation":[20],"of":[21,51,65,159,195,251,269,280,288],"gold":[22],"standard":[23,54],"corpora":[24],"(GSCs),":[25],"however,":[26],"expensive":[28],"time-consuming.":[30],"GSCs":[31],"therefore":[32],"tend":[33],"to":[34,38,306,327,336,345],"be":[35,298,346],"small":[36,105],"focus":[39],"on":[40,80,101,146,165,182,217,232,247,266,285],"specific":[41],"subdomains,":[42],"which":[43,76,88,97],"limits":[44],"their":[45],"usefulness.":[46],"We":[47,69,113,292],"investigated":[48],"the":[49,63,116,134,140,147,162,166,186,190,193,196,200,208,211,214,233,238,245,281,323,332],"use":[50,72],"a":[52,84,89,183,218,248,267,286,299,304,307,313,329,340],"silver":[53],"(SSC)":[56],"that":[57,139,229,294],"automatically":[59],"generated":[60],"by":[61],"combining":[62],"outputs":[64,194],"multiple":[66],"chunking":[67],"systems.":[68],"explored":[70],"two":[71,117,127],"scenarios:":[73],"one":[74,95,150],"are":[78,99],"trained":[79,100,142,164,181,216,231,284],"SSC":[82,148,223,259,296,324],"new":[85],"domain":[86,151,188],"for":[87,143,302],"GSC":[90,106,167,184,219,234,239,249,268,287,308],"not":[92],"available,":[93,103],"although":[104],"but":[107,255],"supplemented":[108,220,256],"with":[109,221,257],"SSC.":[111,191,209],"RESULTS:":[112],"have":[114],"tested":[115],"scenarios":[118],"using":[119,207],"three":[120],"chunkers,":[121],"Lingpipe,":[122],"OpenNLP,":[123],"Yamcha,":[125],"different":[128],"corpora,":[129],"GENIA":[130],"PennBioIE.":[132],"For":[133,210,242],"first":[135],"scenario,":[136,213],"we":[137],"showed":[138,203],"systems":[141,163,215,228,338],"noun-phrase":[144],"recognition":[145],"performed":[152,224,276],"2.7-3.1":[153],"percentage":[154,174],"points":[155,175],"better":[156,226,277],"terms":[158],"F-score":[160],"than":[161,177,227,278],"another":[169],"domain,":[170],"only":[172,252,319],"0.2-0.8":[173],"less":[176],"when":[178,206,237,309],"they":[179],"were":[180,198,230],"same":[187],"as":[189,263],"When":[192],"combined,":[199],"combined":[201,273,317],"system":[202,274,318],"little":[204],"improvement":[205,321],"second":[212],"considerably":[225],"alone,":[235],"especially":[236],"was":[240],"small.":[241],"example,":[243],"training":[244,264,310],"consisting":[250],"10":[253],"abstracts":[254],"yielded":[260],"similar":[261],"performance":[262],"them":[265],"100-250":[270],"abstracts.":[271,290],"even":[275],"any":[279],"individual":[282],"500":[289],"CONCLUSIONS:":[291],"conclude":[293],"can":[297],"viable":[300],"alternative":[301],"or":[303],"supplement":[305,328],"domain.":[315],"A":[316],"shows":[320],"if":[322],"used":[326],"GSC.":[330],"Whether":[331],"approach":[333],"applicable":[335],"other":[337],"natural-language":[341],"processing":[342],"pipeline":[343],"has":[344],"further":[347],"investigated.":[348]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}