{"id":"https://openalex.org/W2292232452","doi":null,"title":"Building a Brazilian Portuguese Parallel Corpus of Original and Simplified Texts","display_name":"Building a Brazilian Portuguese Parallel Corpus of Original and Simplified Texts","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2292232452","mag":"2292232452"},"language":"en","primary_location":{"id":"mag:2292232452","doi":null,"is_oa":false,"landing_page_url":"http://rgcl.wlv.ac.uk/papers/Specia_CICLing2009.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","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":"https://openalex.org/A5087505547","display_name":"Helena de Medeiros Caseli","orcid":"https://orcid.org/0000-0003-3996-8599","observed_orcids":["https://orcid.org/0000-0003-3996-8599"]},"institutions":[{"id":"https://openalex.org/I177909021","display_name":"Universidade Federal de S\u00e3o Carlos","ror":"https://ror.org/00qdc6m37","country_code":"BR","type":"education","lineage":["https://openalex.org/I177909021"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Helena de Medeiros Caseli","raw_affiliation_strings":["Federal University of S\u00e3o Carlos;"],"raw_orcid":"https://orcid.org/0000-0003-3996-8599","affiliations":[{"raw_affiliation_string":"Federal University of S\u00e3o Carlos;","institution_ids":["https://openalex.org/I177909021"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035852991","display_name":"Tiago F. Pereira","orcid":"https://orcid.org/0000-0001-8155-4491","observed_orcids":["https://orcid.org/0000-0001-8155-4491"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiago F. Pereira","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8155-4491","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053217291","display_name":"Lucia Specia","orcid":"https://orcid.org/0000-0002-5495-3128","observed_orcids":["https://orcid.org/0000-0002-5495-3128"]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucia Specia","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0002-5495-3128","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036475121","display_name":"Thiago Alexandre Salgueiro Pardo","orcid":"https://orcid.org/0000-0003-2111-1319","observed_orcids":["https://orcid.org/0000-0003-2111-1319"]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Alexandre Salgueiro Pardo","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0003-2111-1319","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037446132","display_name":"Caroline Gasperin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Caroline Gasperin","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059202822","display_name":"Sandra Maria Alu\u00edsio","orcid":"https://orcid.org/0000-0001-5108-2630","observed_orcids":["https://orcid.org/0000-0001-5108-2630"]},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Sandra Maria Alu\u00edsio","raw_affiliation_strings":["University of S\u00e3o Paulo"],"raw_orcid":"https://orcid.org/0000-0001-5108-2630","affiliations":[{"raw_affiliation_string":"University of S\u00e3o Paulo","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.0708,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.98965597,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.012199999764561653,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-simplification","display_name":"text simplification","score":0.8489999771118164},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.9700000286102295},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.9160000085830688},{"id":"https://openalex.org/keywords/annotation-tools","display_name":"annotation tools","score":0.6190000176429749},{"id":"https://openalex.org/keywords/functional-illiteracy","display_name":"functional illiteracy","score":0.8069999814033508},{"id":"https://openalex.org/keywords/newspaper-texts","display_name":"newspaper texts","score":0.8450000286102295},{"id":"https://openalex.org/keywords/corpus-construction","display_name":"corpus construction","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.750114917755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7397550344467163},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.6144258379936218},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6113683581352234},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.6058017611503601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493710041046143},{"id":"https://openalex.org/C165205368","wikidata":"https://www.wikidata.org/wiki/Q152545","display_name":"Functional illiteracy","level":2,"score":0.5376186966896057},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.49537193775177},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4490339756011963},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.4317364990711212},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4176560044288635},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3923136591911316},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3144547939300537},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2292232452","doi":null,"is_oa":false,"landing_page_url":"http://rgcl.wlv.ac.uk/papers/Specia_CICLing2009.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W48501643","https://openalex.org/W198017583","https://openalex.org/W290860702","https://openalex.org/W1585196265","https://openalex.org/W1830184832","https://openalex.org/W1847917847","https://openalex.org/W2019501487","https://openalex.org/W2078609012","https://openalex.org/W2083245912","https://openalex.org/W2106287264","https://openalex.org/W2109881807","https://openalex.org/W2115416380","https://openalex.org/W2119954850","https://openalex.org/W2133149548","https://openalex.org/W2157423393","https://openalex.org/W2165646132","https://openalex.org/W2180034260","https://openalex.org/W2313285580","https://openalex.org/W2401830275"],"related_works":["https://openalex.org/W7095527412","https://openalex.org/W7099745445","https://openalex.org/W182063109","https://openalex.org/W1963741647","https://openalex.org/W1838004822","https://openalex.org/W7098089705","https://openalex.org/W2045320784","https://openalex.org/W2888322581","https://openalex.org/W2106287264","https://openalex.org/W7100154483"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"address":[4],"the":[5,9,25,58,94,105,110],"problem":[6],"of":[7,48,63,66,75,85,96,104],"building":[8],"necessary":[10],"tools":[11],"and":[12,27,40,60,68,80,88,117],"resources":[13,111],"for":[14],"performing":[15],"Brazilian":[16],"Portuguese":[17],"text":[18,126],"simplification.":[19,127],"We":[20,99],"describe":[21],"our":[22],"efforts":[23],"on":[24],"design":[26],"development":[28],"of:":[29],"(a)":[30],"a":[31,42,64],"XCES-based":[32],"annotation":[33,37],"schema,":[34],"(b)":[35],"an":[36,102,123],"edition":[38],"tool,":[39],"(c)":[41],"portal":[43],"to":[44,55],"access":[45],"parallel":[46],"corpora":[47],"original-simplified":[49],"texts.":[50],"These":[51],"contributions":[52],"were":[53],"intended":[54],"(i)":[56],"allow":[57],"creation":[59,95],"public":[61],"release":[62],"corpus":[65,107],"original":[67],"simplified":[69,119],"texts":[70,116],"with":[71],"two":[72,83],"different":[73],"versions":[74],"simplification":[76,91],"(called":[77],"here":[78],"natural":[79],"strong),":[81],"targeting":[82],"levels":[84],"functional":[86],"illiteracy":[87],"(ii)":[89],"register":[90],"decisions":[92],"during":[93],"such":[97],"corpus.":[98],"also":[100],"provide":[101],"analysis":[103],"first":[106],"created":[108],"using":[109],"presented":[112],"here:":[113],"104":[114],"newspaper":[115],"their":[118],"versions,":[120],"produced":[121],"by":[122],"expert":[124],"in":[125]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
