{"id":"https://openalex.org/W2786987907","doi":null,"title":"Detection of Text Reuse in French Medical Corpora.","display_name":"Detection of Text Reuse in French Medical Corpora.","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2786987907","mag":"2786987907"},"language":"en","primary_location":{"id":"mag:2786987907","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/W16-5112/","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Eva D\u2019Hondt","orcid":"https://orcid.org/0000-0001-5646-2261","observed_orcids":["https://orcid.org/0000-0001-5646-2261"]},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Eva D\u2019Hondt","raw_affiliation_strings":["Radboud University Nijmegen, Nijmegen, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-5646-2261","affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047002517","display_name":"Cyril Grouin","orcid":"https://orcid.org/0000-0001-5809-188X","observed_orcids":["https://orcid.org/0000-0001-5809-188X"]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cyril Grouin","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005499870","display_name":"Aur\u00e9lie N\u00e9v\u00e9ol","orcid":"https://orcid.org/0000-0002-1846-9144","observed_orcids":["https://orcid.org/0000-0002-1846-9144"]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aur\u00e9lie N\u00e9v\u00e9ol","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"raw_orcid":"https://orcid.org/0000-0002-1846-9144","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061737423","display_name":"Efstathios Stamatatos","orcid":"https://orcid.org/0000-0002-1336-9128","observed_orcids":["https://orcid.org/0000-0002-1336-9128"]},"institutions":[{"id":"https://openalex.org/I98805295","display_name":"University of the Aegean","ror":"https://ror.org/03zsp3p94","country_code":"GR","type":"education","lineage":["https://openalex.org/I98805295"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Efstathios Stamatatos","raw_affiliation_strings":["University of the Aegean, Mytilene, Greece"],"raw_orcid":"https://orcid.org/0000-0002-1336-9128","affiliations":[{"raw_affiliation_string":"University of the Aegean, Mytilene, Greece","institution_ids":["https://openalex.org/I98805295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090195478","display_name":"Pierre Zweigenbaum","orcid":"https://orcid.org/0000-0001-8410-4808","observed_orcids":["https://orcid.org/0000-0001-8410-4808"]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Zweigenbaum","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"raw_orcid":"https://orcid.org/0000-0001-8410-4808","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34755486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7480000257492065,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.7480000257492065,"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"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.056699998676776886,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.031599998474121094,"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/text-reuse-detection","display_name":"text reuse detection","score":0.996999979019165},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.9330000281333923},{"id":"https://openalex.org/keywords/document-deduplication","display_name":"document deduplication","score":0.7680000066757202},{"id":"https://openalex.org/keywords/document-versioning","display_name":"document versioning","score":0.5799999833106995},{"id":"https://openalex.org/keywords/ocr-errors","display_name":"OCR errors","score":0.7369999885559082},{"id":"https://openalex.org/keywords/de-identification","display_name":"de-identification","score":0.968999981880188},{"id":"https://openalex.org/keywords/duplicate-detection","display_name":"duplicate detection","score":0.4480000138282776},{"id":"https://openalex.org/keywords/secondary-use-of-health-data","display_name":"secondary use of health data","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838448286056519},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.7721322178840637},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.6885373592376709},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5782583951950073},{"id":"https://openalex.org/C3019659195","wikidata":"https://www.wikidata.org/wiki/Q5690566","display_name":"Meaningful use","level":3,"score":0.5453783869743347},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.5187404751777649},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5078666806221008},{"id":"https://openalex.org/C3020144179","wikidata":"https://www.wikidata.org/wiki/Q10871684","display_name":"Electronic health record","level":3,"score":0.47580891847610474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3744826018810272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3320106267929077},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.24585214257240295},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08218130469322205},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2786987907","doi":null,"is_oa":false,"landing_page_url":"https://aclanthology.org/W16-5112/","pdf_url":null,"source":{"id":"https://openalex.org/S4306419219","display_name":"International Conference on Computational Linguistics","issn_l":"1525-2477","issn":["1525-2477"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Computational Linguistics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W256669079","https://openalex.org/W1262131959","https://openalex.org/W1919152067","https://openalex.org/W1967043694","https://openalex.org/W1974336599","https://openalex.org/W1984291951","https://openalex.org/W1990061958","https://openalex.org/W2010347687","https://openalex.org/W2015620729","https://openalex.org/W2023228526","https://openalex.org/W2032503600","https://openalex.org/W2072828027","https://openalex.org/W2073265902","https://openalex.org/W2089119080","https://openalex.org/W2106921977","https://openalex.org/W2119455368","https://openalex.org/W2146408445","https://openalex.org/W2158331042","https://openalex.org/W2250944293","https://openalex.org/W2251338372"],"related_works":["https://openalex.org/W2250944293","https://openalex.org/W3105369136","https://openalex.org/W2146408445","https://openalex.org/W7097777106","https://openalex.org/W3165274855","https://openalex.org/W2250424592","https://openalex.org/W7015764069","https://openalex.org/W6927297970","https://openalex.org/W2089994405","https://openalex.org/W2291549117"],"abstract_inverted_index":{"Electronic":[0],"Health":[1],"Records":[2],"(EHRs)":[3],"are":[4],"increasingly":[5],"available":[6],"in":[7,20,46,74,119],"modern":[8],"health":[9,22],"care":[10],"institutions":[11],"either":[12],"through":[13,26],"the":[14,27,38,50,66,78,84,89],"direct":[15],"creation":[16,35],"of":[17,29,68,71,80,83,91,130,142],"electronic":[18],"documents":[19],"hospitals\u2019":[21],"information":[23],"systems,":[24],"or":[25,102],"digitization":[28],"historical":[30],"paper":[31],"records.":[32],"Each":[33],"EHR":[34,51,122],"method":[36,112],"yields":[37],"need":[39],"for":[40,53],"sophisticated":[41],"text":[42,72,109],"reuse":[43,73,110],"detection":[44,67,79,90,111],"tools":[45],"order":[47],"to":[48,100,113],"prepare":[49],"collections":[52],"efficient":[54],"secondary":[55],"use":[56],"relying":[57],"on":[58],"Natural":[59],"Language":[60],"Processing":[61],"methods.":[62],"Herein,":[63],"we":[64],"address":[65],"two":[69,120],"types":[70],"French":[75,121],"EHRs:":[76],"1)":[77],"updated":[81],"versions":[82],"same":[85],"document":[86,92,117,140],"and":[87,132,135],"2)":[88],"duplicates":[93],"that":[94,124],"still":[95],"bear":[96],"surface":[97],"differences":[98],"due":[99],"OCR":[101],"de-identification":[103],"processing.":[104],"We":[105],"present":[106],"a":[107],"robust":[108],"automatically":[114],"identify":[115],"redundant":[116,139],"pairs":[118,141],"corpora":[123],"achieves":[125],"an":[126],"overall":[127],"macro":[128],"F-measure":[129],"0.68":[131],"0.60,":[133],"respectively":[134],"correctly":[136],"identifies":[137],"all":[138],"interest.":[143]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2018-02-23T00:00:00"}
