{"id":"https://openalex.org/W2109757083","doi":"https://doi.org/10.1109/icdar.2003.1227694","title":"A segmentation method for bibliographic references by contextual tagging of fields","display_name":"A segmentation method for bibliographic references by contextual tagging of fields","publication_year":2004,"publication_date":"2004-02-03","ids":{"openalex":"https://openalex.org/W2109757083","doi":"https://doi.org/10.1109/icdar.2003.1227694","mag":"2109757083"},"language":"en","primary_location":{"id":"doi:10.1109/icdar.2003.1227694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00107677","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048736038","display_name":"Dominique Besagni","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1295345811","display_name":"Institut de l'Information Scientifique et Technique","ror":"https://ror.org/02mn0vt57","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1295345811","https://openalex.org/I4210140053"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"D. Besagni","raw_affiliation_strings":["INIST-CNRS, URI, Vandoeuvre-les-Nancy, France"],"affiliations":[{"raw_affiliation_string":"INIST-CNRS, URI, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I1295345811","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002810227","display_name":"Abdel Bela\u0131\u0308d","orcid":"https://orcid.org/0000-0002-9107-1204"},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"A. Belaid","raw_affiliation_strings":["CNRS Campus scientifique, LORIA, Vandoeuvre-les-Nancy, France"],"affiliations":[{"raw_affiliation_string":"CNRS Campus scientifique, LORIA, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044822818","display_name":"Nelly Benet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"N. Benet","raw_affiliation_strings":["CNRS Campus scientifique, LORIA, Vandoeuvre-les-Nancy, France"],"affiliations":[{"raw_affiliation_string":"CNRS Campus scientifique, LORIA, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048736038"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1295345811"],"apc_list":null,"apc_paid":null,"fwci":2.0725,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.87045516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"384","last_page":"388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9958000183105469,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9934999942779541,"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/ascii","display_name":"ASCII","score":0.8291805982589722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8195600509643555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6376180052757263},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6093611717224121},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5950047373771667},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5908375382423401},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5271363258361816},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5240429043769836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5213464498519897},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.4911160171031952},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4806888997554779},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4517107605934143},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14230671525001526},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13790854811668396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08901727199554443}],"concepts":[{"id":"https://openalex.org/C196832560","wikidata":"https://www.wikidata.org/wiki/Q8815","display_name":"ASCII","level":2,"score":0.8291805982589722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195600509643555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6376180052757263},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6093611717224121},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5950047373771667},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5908375382423401},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5271363258361816},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5240429043769836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5213464498519897},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.4911160171031952},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4806888997554779},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4517107605934143},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14230671525001526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13790854811668396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08901727199554443},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdar.2003.1227694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdar.2003.1227694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.4479","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.4479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csc.liv.ac.uk/~prima/ICDAR2003/Papers/0070_615_besagni_d.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00107677v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00107677","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Seventh International Conference on Document Analysis and Recognition, Aug 2003, Edinburgh, United Kingdom. 5 p","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00107677v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00107677","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Seventh International Conference on Document Analysis and Recognition, Aug 2003, Edinburgh, United Kingdom. 5 p","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2008388219","https://openalex.org/W2034860184","https://openalex.org/W2053549370","https://openalex.org/W2081687495","https://openalex.org/W2154498027"],"related_works":["https://openalex.org/W3021015524","https://openalex.org/W2256275460","https://openalex.org/W2228320762","https://openalex.org/W3195037996","https://openalex.org/W110684752","https://openalex.org/W51586780","https://openalex.org/W1484753961","https://openalex.org/W2157319784","https://openalex.org/W2915975171","https://openalex.org/W2918151804"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,20,40,45,105,117],"method":[4,17,37],"based":[5],"on":[6,19,120],"part-of-speech":[7],"tagging":[8],"(PoS)":[9],"is":[10],"used":[11],"for":[12],"bibliographic":[13],"reference":[14,34],"structure.":[15],"This":[16],"operates":[18,115],"roughly":[21],"structured":[22],"ASCII":[23],"file,":[24],"produced":[25],"by":[26,97],"OCR.":[27],"Because":[28],"of":[29,32],"the":[30,33,36],"heterogeneity":[31],"structure,":[35],"acts":[38],"in":[39,63,74,92],"bottom-up":[41],"way,":[42],"without":[43],"an":[44],"priori":[46],"model,":[47],"gathering":[48],"structural":[49],"elements":[50],"from":[51,109,143],"basic":[52],"tags":[53,59],"to":[54,67,78],"sub-fields":[55],"and":[56,71,124,136],"fields.":[57],"Significant":[58],"are":[60,90,133,140],"first":[61],"grouped":[62],"homogeneous":[64],"classes":[65],"according":[66],"their":[68],"grammar":[69],"categories":[70],"then":[72],"reduced":[73],"canonical":[75],"forms":[76],"corresponding":[77],"record":[79,122],"fields:":[80],"\"authors\",":[81],"\"title\",":[82],"\"conference":[83],"name\",":[84],"\"date\",":[85],"etc.":[86],"Non":[87],"labelled":[88],"tokens":[89],"integrated":[91],"one":[93],"or":[94,103],"another":[95],"field":[96],"either":[98],"applying":[99],"PoS":[100],"correction":[101],"rules":[102],"using":[104],"structure":[106],"model":[107],"generated":[108],"well-detected":[110],"records.":[111],"The":[112],"designed":[113],"prototype":[114],"with":[116],"great":[118],"satisfaction":[119],"different":[121],"layouts":[123],"character":[125],"recognition":[126],"qualities.":[127],"Without":[128],"manual":[129],"intervention,":[130],"96.6%":[131],"words":[132],"correctly":[134],"attributed,":[135],"about":[137],"75.9%":[138],"references":[139],"completely":[141],"segmented":[142],"2500":[144],"references.":[145]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
