{"id":"https://openalex.org/W2130371208","doi":"https://doi.org/10.1186/1471-2105-12-s3-s7","title":"A structural SVM approach for reference parsing","display_name":"A structural SVM approach for reference parsing","publication_year":2011,"publication_date":"2011-06-09","ids":{"openalex":"https://openalex.org/W2130371208","doi":"https://doi.org/10.1186/1471-2105-12-s3-s7","mag":"2130371208","pmid":"https://pubmed.ncbi.nlm.nih.gov/21658294"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-12-s3-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S7","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/10.1186/1471-2105-12-S3-S7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101656513","display_name":"Xiaoli Zhang","orcid":"https://orcid.org/0000-0002-0918-2483"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaoli Zhang","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. zhangxiaol@mail.nih.gov","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. zhangxiaol@mail.nih.gov","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585404","display_name":"Jie Zou","orcid":"https://orcid.org/0000-0003-2359-6401"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Zou","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101509629","display_name":"Daniel Le","orcid":"https://orcid.org/0000-0002-0220-6366"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel X Le","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103701816","display_name":"George R. Thoma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George R Thoma","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA#TAB#","institution_ids":["https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101656513"],"corresponding_institution_ids":["https://openalex.org/I2800548410","https://openalex.org/I4210109390"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.3992,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.63383436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"12","issue":"S3","first_page":"S7","last_page":"S7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.2184000015258789,"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":0.2184000015258789,"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":0.21809999644756317,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.15000000596046448,"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/support-vector-machine","display_name":"Support vector machine","score":0.8759937286376953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8178079128265381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7027695178985596},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6777390241622925},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6485656499862671},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5214583277702332},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4475635886192322},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4367116689682007},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.41795432567596436},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3627030849456787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3521471917629242}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.8759937286376953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178079128265381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7027695178985596},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6777390241622925},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6485656499862671},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5214583277702332},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4475635886192322},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4367116689682007},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.41795432567596436},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3627030849456787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3521471917629242},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","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}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-12-s3-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S7","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:21658294","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21658294","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:pubmedcentral.nih.gov:3111593","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3111593","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-12-s3-s7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S7","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314788","display_name":"Lister Hill National Center for Biomedical Communications","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2130371208.pdf","grobid_xml":"https://content.openalex.org/works/W2130371208.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W166924812","https://openalex.org/W1513141203","https://openalex.org/W1519749309","https://openalex.org/W1531887935","https://openalex.org/W1559499673","https://openalex.org/W1573596790","https://openalex.org/W2018295102","https://openalex.org/W2031248101","https://openalex.org/W2037264753","https://openalex.org/W2078517869","https://openalex.org/W2105395040","https://openalex.org/W2109757083","https://openalex.org/W2127484150","https://openalex.org/W2130160813","https://openalex.org/W2145130412","https://openalex.org/W2147880316","https://openalex.org/W2153635508","https://openalex.org/W2154498027","https://openalex.org/W2163737492","https://openalex.org/W2429914308","https://openalex.org/W3120421331","https://openalex.org/W4244512068"],"related_works":["https://openalex.org/W2061848042","https://openalex.org/W1837849430","https://openalex.org/W2171578666","https://openalex.org/W1989442767","https://openalex.org/W2148251896","https://openalex.org/W2074870855","https://openalex.org/W1542929759","https://openalex.org/W2345184372","https://openalex.org/W2313060652","https://openalex.org/W3013515612"],"abstract_inverted_index":{"BACKGROUND:":[0],"Automated":[1],"extraction":[2],"of":[3,21,31,110,211,224,234],"bibliographic":[4,42],"data,":[5],"such":[6],"as":[7],"article":[8],"titles,":[9],"author":[10],"names,":[11],"abstracts,":[12],"and":[13,80,106,128,141,156,163,206,242],"references":[14,69],"is":[15,55,207],"essential":[16],"to":[17,48,72,81,113,144,182,209],"the":[18,29,187,193,216,231],"affordable":[19],"creation":[20],"large":[22],"citation":[23],"databases.":[24],"References,":[25],"typically":[26],"appearing":[27],"at":[28,161],"end":[30],"journal":[32],"articles,":[33],"can":[34],"also":[35,138],"provide":[36],"valuable":[37],"information":[38],"for":[39,134,173],"extracting":[40],"other":[41],"data.":[43],"Therefore,":[44],"parsing":[45,75,96],"individual":[46],"reference":[47,74,135,255],"extract":[49],"author,":[50],"title,":[51],"journal,":[52],"year,":[53],"etc.":[54],"sometimes":[56],"a":[57,76,89],"necessary":[58],"preprocessing":[59],"step":[60],"in":[61,68,254],"building":[62],"citation-indexing":[63],"systems.":[64],"The":[65,149,222],"regular":[66],"structure":[67],"enables":[70],"us":[71],"consider":[73],"sequence":[77,251],"learning":[78,93,252],"problem":[79],"study":[82],"structural":[83,104,115,142,154,176,212,240],"Support":[84],"Vector":[85],"Machine":[86],"(structural":[87],"SVM),":[88],"newly":[90],"developed":[91],"structured":[92],"algorithm":[94],"on":[95],"references.":[97],"RESULTS:":[98],"In":[99],"this":[100],"study,":[101],"we":[102],"implemented":[103],"SVM":[105,116,140,143,155,177,183,202,213,241],"used":[107,172],"two":[108,226],"types":[109],"contextual":[111,188,194,219],"features":[112,170,196,236],"compare":[114],"with":[117,228],"conventional":[118],"SVM.":[119],"Both":[120],"methods":[121,227],"achieve":[122,158],"above":[123,129],"98%":[124],"token":[125],"classification":[126],"accuracy":[127,133],"95%":[130],"overall":[131],"chunk-level":[132],"parsing.":[136,256],"We":[137],"compared":[139,181],"Conditional":[145],"Random":[146],"Field":[147],"(CRF).":[148],"experimental":[150],"results":[151],"show":[152,237],"that":[153,210,238],"CRF":[157,229,243],"similar":[159],"accuracies":[160],"token-":[162],"chunk-levels.":[164],"CONCLUSIONS:":[165],"When":[166],"only":[167],"basic":[168],"observation":[169,195,220],"are":[171,200],"each":[174],"token,":[175],"achieves":[178],"higher":[179],"performance":[180,203],"since":[184],"it":[185],"utilizes":[186],"label":[189],"features.":[190,221],"However,":[191],"when":[192],"from":[197],"neighboring":[198],"tokens":[199],"combined,":[201],"improves":[204],"greatly,":[205],"close":[208],"after":[214],"adding":[215],"second":[217],"order":[218],"comparison":[223],"these":[225],"using":[230],"same":[232],"set":[233],"binary":[235],"both":[239],"perform":[244],"better":[245],"than":[246],"SVM,":[247],"indicating":[248],"their":[249],"stronger":[250],"ability":[253]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}