{"id":"https://openalex.org/W4403278709","doi":"https://doi.org/10.1109/is61756.2024.10705189","title":"TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers","display_name":"TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers","publication_year":2024,"publication_date":"2024-08-29","ids":{"openalex":"https://openalex.org/W4403278709","doi":"https://doi.org/10.1109/is61756.2024.10705189"},"language":"en","primary_location":{"id":"doi:10.1109/is61756.2024.10705189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5113426444","display_name":"S. Baghdadi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143287","display_name":"Institut de Recherche Technologique B-com","ror":"https://ror.org/03cejhk28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210143287"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sarra Baghdadi","raw_affiliation_strings":["Institute of Research and Technology b-com,Rennes,France"],"affiliations":[{"raw_affiliation_string":"Institute of Research and Technology b-com,Rennes,France","institution_ids":["https://openalex.org/I4210143287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032528704","display_name":"Majd Saleh","orcid":"https://orcid.org/0000-0003-1800-0028"},"institutions":[{"id":"https://openalex.org/I4210143287","display_name":"Institut de Recherche Technologique B-com","ror":"https://ror.org/03cejhk28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210143287"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Majd Saleh","raw_affiliation_strings":["Institute of Research and Technology b-com,Rennes,France"],"affiliations":[{"raw_affiliation_string":"Institute of Research and Technology b-com,Rennes,France","institution_ids":["https://openalex.org/I4210143287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083746253","display_name":"St\u00e9phane Paquelet","orcid":"https://orcid.org/0000-0002-6874-8336"},"institutions":[{"id":"https://openalex.org/I4210143287","display_name":"Institut de Recherche Technologique B-com","ror":"https://ror.org/03cejhk28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210143287"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"St\u00e9phane Paquelet","raw_affiliation_strings":["Institute of Research and Technology b-com,Rennes,France"],"affiliations":[{"raw_affiliation_string":"Institute of Research and Technology b-com,Rennes,France","institution_ids":["https://openalex.org/I4210143287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113426444"],"corresponding_institution_ids":["https://openalex.org/I4210143287"],"apc_list":null,"apc_paid":null,"fwci":0.2384,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52940243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9502999782562256,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.666675865650177},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5605150461196899},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13958778977394104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09919324517250061},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0954904556274414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666675865650177},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5605150461196899},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13958778977394104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09919324517250061},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0954904556274414}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is61756.2024.10705189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W2064675550","https://openalex.org/W2396881363","https://openalex.org/W2493916176","https://openalex.org/W2963716420","https://openalex.org/W2997244287","https://openalex.org/W3003711898","https://openalex.org/W3102373121","https://openalex.org/W6620707391","https://openalex.org/W6635432498","https://openalex.org/W6636510571","https://openalex.org/W6638575021","https://openalex.org/W6638891705","https://openalex.org/W6639619044","https://openalex.org/W6682691769","https://openalex.org/W6712016711","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6749811377","https://openalex.org/W6755207826","https://openalex.org/W6767552790","https://openalex.org/W6786202787","https://openalex.org/W6797211622","https://openalex.org/W6856289622","https://openalex.org/W6860171411"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Text":[0],"segmentation":[1,82,126,135],"holds":[2],"paramount":[3],"importance":[4],"in":[5,18,145],"the":[6,52,85,95],"field":[7],"of":[8,54,94,100,111,118],"Natural":[9],"Language":[10],"Processing":[11],"(NLP).":[12],"It":[13,114,137],"plays":[14],"an":[15,116],"important":[16],"role":[17],"several":[19],"NLP":[20],"downstream":[21],"tasks":[22],"like":[23],"information":[24],"retrieval":[25],"and":[26,56,128],"document":[27],"summarization.":[28],"In":[29],"this":[30],"work,":[31],"we":[32],"propose":[33],"a":[34,47,67,79,106,123,132,139],"new":[35],"solution,":[36,143],"namely":[37],"TocBERT,":[38],"for":[39],"segmenting":[40],"texts":[41],"using":[42],"bidirectional":[43],"transformers.":[44],"TocBERT":[45,101],"represents":[46],"supervised":[48],"solution":[49,74],"trained":[50],"on":[51,78,105,122,131],"detection":[53],"titles":[55,147],"sub-titles":[57],"from":[58,148],"their":[59],"semantic":[60],"representations.":[61],"This":[62],"task":[63],"was":[64],"formulated":[65],"as":[66],"named":[68],"entity":[69],"recognition":[70],"(NER)":[71],"problem.":[72,136],"The":[73,98],"has":[75,102],"been":[76,103],"applied":[77],"medical":[80],"text":[81,125,134],"use-case":[83],"where":[84],"Bio-ClinicalBERT":[86],"model":[87],"is":[88],"fine-tuned":[89],"to":[90],"segment":[91],"discharge":[92],"summaries":[93],"MIMIC-III":[96],"dataset.":[97],"performance":[99],"evaluated":[104,121],"human-labeled":[107],"ground":[108],"truth":[109],"corpus":[110],"250":[112],"notes.":[113],"achieved":[115],"F1-score":[117],"84.6%":[119],"when":[120],"linear":[124],"problem":[127],"72.8":[129],"%":[130],"hierarchical":[133],"outperformed":[138],"carefully":[140],"designed":[141],"rule-based":[142],"particularly":[144],"distinguishing":[146],"subtitles.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}