{"id":"https://openalex.org/W3036850497","doi":"https://doi.org/10.3233/shti200183","title":"Parallel Sentence Alignment from Biomedical Comparable Corpora","display_name":"Parallel Sentence Alignment from Biomedical Comparable Corpora","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3036850497","doi":"https://doi.org/10.3233/shti200183","mag":"3036850497","pmid":"https://pubmed.ncbi.nlm.nih.gov/32570407"},"language":"en","primary_location":{"id":"doi:10.3233/shti200183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti200183","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/shti200183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cardon R\u00e9mi","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":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Cardon R\u00e9mi","raw_affiliation_strings":["UMR CNRS 8163 - STL, F-59000 Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR CNRS 8163 - STL, F-59000 Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":null,"display_name":"Grabar Natalia","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":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Grabar Natalia","raw_affiliation_strings":["UMR CNRS 8163 - STL, F-59000 Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UMR CNRS 8163 - STL, F-59000 Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970"],"apc_list":null,"apc_paid":null,"fwci":0.275,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53976117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"270","issue":null,"first_page":"362","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.8705328106880188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7067224383354187},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6505251526832581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6182392239570618},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6048594117164612},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5649996995925903},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4982938766479492},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.47503215074539185},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.43149715662002563},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.4308134913444519},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4111970067024231},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3898767828941345},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.1751435399055481},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11034855246543884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8705328106880188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7067224383354187},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6505251526832581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182392239570618},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6048594117164612},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5649996995925903},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4982938766479492},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.47503215074539185},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.43149715662002563},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.4308134913444519},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4111970067024231},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3898767828941345},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.1751435399055481},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11034855246543884},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","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":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D032882","descriptor_name":"Comprehension","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.3233/shti200183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti200183","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:32570407","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32570407","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":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:HAL:hal-03095183v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03095183","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Studies in Health Technology and Informatics, 270, pp.362-366, 2020, &#x27E8;10.3233/SHTI200183&#x27E9;","raw_type":"Book sections"},{"id":"pmh:oai:lilloa.univ-lille.fr:20.500.12210/64227","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.12210/64227","pdf_url":null,"source":{"id":"https://openalex.org/S4306402203","display_name":"LillOA (Universit\u00e9 de Lille (University Of Lille))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123514","host_organization_name":"Centre d'Etudes en Civilisations, Langues et Litt\u00e9ratures Etrang\u00e8res","host_organization_lineage":["https://openalex.org/I4210123514"],"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":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.3233/shti200183","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti200183","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1493309689","https://openalex.org/W1647671624","https://openalex.org/W2053154970","https://openalex.org/W2101234009","https://openalex.org/W2106952837","https://openalex.org/W2129500526","https://openalex.org/W2159014656","https://openalex.org/W2462305634","https://openalex.org/W2508865106","https://openalex.org/W2565770050","https://openalex.org/W2734531809","https://openalex.org/W2909677514","https://openalex.org/W4388152766"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Parallel":[0,18],"sentences":[1,19,134],"provide":[2],"semantically":[3],"similar":[4],"information":[5],"which":[6,79],"can":[7,28,124],"vary":[8],"on":[9],"a":[10,48,130],"given":[11,49],"dimension,":[12],"such":[13,70],"as":[14,111],"language":[15],"or":[16],"register.":[17],"with":[20],"register":[21],"variation":[22],"(like":[23],"expert":[24],"and":[25,46,62,86,91,100],"non-expert":[26],"documents)":[27],"be":[29,125],"exploited":[30],"for":[31],"the":[32,52,104,119],"automatic":[33,39],"text":[34,40],"simplification.":[35],"The":[36],"aim":[37],"of":[38,132],"simplification":[41,55],"is":[42,67],"to":[43,59,75,89,103,127],"better":[44],"access":[45],"understand":[47,60],"information.":[50],"In":[51],"biomedical":[53,105],"field,":[54],"may":[56],"permit":[57],"patients":[58],"medical":[61],"health":[63],"texts.":[64],"Yet,":[65],"there":[66],"currently":[68],"no":[69],"available":[71],"resources.":[72],"We":[73,107],"propose":[74],"exploit":[76],"comparable":[77,137],"corpora":[78,96],"are":[80,97,101],"distinguished":[81],"by":[82],"their":[83],"registers":[84],"(specialized":[85],"simplified":[87],"versions)":[88],"detect":[90],"align":[92],"parallel":[93,133],"sentences.":[94],"These":[95],"in":[98],"French":[99],"related":[102],"area.":[106],"treat":[108],"this":[109],"task":[110],"binary":[112],"classification":[113],"(alignment/non-alignment).":[114],"Our":[115],"results":[116],"show":[117],"that":[118],"method":[120],"we":[121],"present":[122],"here":[123],"used":[126],"automatically":[128],"generate":[129],"corpus":[131],"from":[135],"our":[136],"corpus.":[138]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}
