{"id":"https://openalex.org/W2999304711","doi":"https://doi.org/10.26615/978-954-452-056-4_020","title":"Parallel Sentence Retrieval From Comparable Corpora for Biomedical Text Simplification","display_name":"Parallel Sentence Retrieval From Comparable Corpora for Biomedical Text Simplification","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2999304711","doi":"https://doi.org/10.26615/978-954-452-056-4_020","mag":"2999304711"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_020","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_020","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_020","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"UMR CNRS 8163 \u2013 STL, Lille, France","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":"UMR CNRS 8163 \u2013 STL, Lille, France","raw_affiliation_strings":["UMR CNRS 8163 -STL F-59000 Lille, France"],"affiliations":[{"raw_affiliation_string":"UMR CNRS 8163 -STL F-59000 Lille, France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025603922","display_name":"R\u00e9mi Cardon","orcid":"https://orcid.org/0000-0002-7858-3504"},"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":"R\u00e9mi Cardon","raw_affiliation_strings":["UMR CNRS 8163 -STL F-59000 Lille, France"],"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":"https://openalex.org/A5007781745","display_name":"Natalia Grabar","orcid":"https://orcid.org/0000-0002-0237-4554"},"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":"Natalia Grabar","raw_affiliation_strings":["UMR CNRS 8163 -STL F-59000 Lille, France"],"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":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970"],"apc_list":null,"apc_paid":null,"fwci":0.289,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68653205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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":0.9944999814033508,"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":0.8883762955665588},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7191392183303833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6809931993484497},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6320000886917114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6245211958885193},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5358847975730896},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5332640409469604},{"id":"https://openalex.org/keywords/text-simplification","display_name":"Text simplification","score":0.5225797891616821},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5135383605957031},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4969477951526642},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.4576534032821655},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4472424387931824},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.4400673806667328},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4335029423236847},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4110376834869385},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.22567281126976013},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09145477414131165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8883762955665588},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7191392183303833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6809931993484497},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6320000886917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6245211958885193},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5358847975730896},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5332640409469604},{"id":"https://openalex.org/C59415355","wikidata":"https://www.wikidata.org/wiki/Q3484781","display_name":"Text simplification","level":3,"score":0.5225797891616821},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5135383605957031},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4969477951526642},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.4576534032821655},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4472424387931824},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.4400673806667328},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4335029423236847},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4110376834869385},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.22567281126976013},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09145477414131165},{"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/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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26615/978-954-452-056-4_020","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_020","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-115969","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-115969","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_020","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_020","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_020","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3312464302","display_name":null,"funder_award_id":"CE19-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6803667113","display_name":null,"funder_award_id":"ANR-17","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8067288029","display_name":"Communication, Literacy, Education, Accessibility, Readability","funder_award_id":"ANR-17-CE19-0016","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2999304711.pdf","grobid_xml":"https://content.openalex.org/works/W2999304711.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1486649854","https://openalex.org/W1493309689","https://openalex.org/W1566018662","https://openalex.org/W1647671624","https://openalex.org/W1952210680","https://openalex.org/W1967043694","https://openalex.org/W1995514968","https://openalex.org/W2020777959","https://openalex.org/W2053154970","https://openalex.org/W2061235289","https://openalex.org/W2093219119","https://openalex.org/W2101234009","https://openalex.org/W2102381086","https://openalex.org/W2106612368","https://openalex.org/W2106952837","https://openalex.org/W2109802560","https://openalex.org/W2126286303","https://openalex.org/W2133458109","https://openalex.org/W2135875128","https://openalex.org/W2138238299","https://openalex.org/W2152180407","https://openalex.org/W2153579005","https://openalex.org/W2159014656","https://openalex.org/W2165578718","https://openalex.org/W2250305120","https://openalex.org/W2250387780","https://openalex.org/W2250503148","https://openalex.org/W2251044566","https://openalex.org/W2251427843","https://openalex.org/W2251919380","https://openalex.org/W2296307963","https://openalex.org/W2462305634","https://openalex.org/W2500036977","https://openalex.org/W2508865106","https://openalex.org/W2561363829","https://openalex.org/W2565770050","https://openalex.org/W2574026469","https://openalex.org/W2576026769","https://openalex.org/W2734531809","https://openalex.org/W2905409886","https://openalex.org/W2909677514","https://openalex.org/W2911964244","https://openalex.org/W2963355447","https://openalex.org/W4294170691","https://openalex.org/W4388152766"],"related_works":["https://openalex.org/W4283817051","https://openalex.org/W287472456","https://openalex.org/W2578713317","https://openalex.org/W4386106350","https://openalex.org/W4302947181","https://openalex.org/W2141068210","https://openalex.org/W2000983314","https://openalex.org/W3198859326","https://openalex.org/W3147887346","https://openalex.org/W3117142879"],"abstract_inverted_index":{"Parallel":[0,18],"sentences":[1,19,128,180],"provide":[2],"semantically":[3],"similar":[4],"information":[5],"which":[6,79],"can":[7,28,132,170],"vary":[8],"on":[9,155],"a":[10,48,121,149,176],"given":[11,49,122],"dimension,":[12],"such":[13,70],"as":[14,141],"language":[15],"or":[16,135],"register.":[17],"with":[20,148],"register":[21],"variation":[22],"(like":[23],"expert":[24],"and":[25,46,62,86,91,100,126,131,154],"non-expert":[26],"documents)":[27],"be":[29,133,171],"exploited":[30],"for":[31],"the":[32,52,104,156,165],"automatic":[33,39],"text":[34,40],"simplification.":[35],"The":[36],"aim":[37],"of":[38,124,152,178],"simplification":[41,55],"is":[42,67,117,129],"to":[43,59,75,89,103,118,173],"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":[73,137,145],"propose":[74],"exploit":[76],"comparable":[77,183],"corpora":[78,96],"are":[80,97,101],"distinguished":[81],"by":[82],"their":[83],"registers":[84],"(specialized":[85],"simplified":[87,127],"versions)":[88],"detect":[90],"align":[92],"parallel":[93,130,179],"sentences.":[94],"These":[95],"in":[98],"French":[99],"related":[102],"area.":[106],"Manually":[107],"created":[108],"reference":[109],"data":[110],"show":[111,163],"0.76":[112],"inter-annotator":[113],"agreement.":[114],"Our":[115,161],"purpose":[116],"state":[119],"whether":[120],"pair":[123],"specialized":[125],"aligned":[134],"not.":[136],"treat":[138],"this":[139],"task":[140],"binary":[142],"classification":[143],"(alignment/nonalignment).":[144],"perform":[146],"experiments":[147],"controlled":[150],"ratio":[151],"imbalance":[153],"highly":[157],"unbalanced":[158],"real":[159],"data.":[160],"results":[162],"that":[164],"method":[166],"we":[167],"present":[168],"here":[169],"used":[172],"automatically":[174],"generate":[175],"corpus":[177],"from":[181],"our":[182],"corpus.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-01-23T00:00:00"}