{"id":"https://openalex.org/W4293235253","doi":"https://doi.org/10.1142/s219688882250021x","title":"Semi-Automatic Construction of a Readability Corpus for the Vietnamese Language","display_name":"Semi-Automatic Construction of a Readability Corpus for the Vietnamese Language","publication_year":2022,"publication_date":"2022-04-22","ids":{"openalex":"https://openalex.org/W4293235253","doi":"https://doi.org/10.1142/s219688882250021x"},"language":"en","primary_location":{"id":"doi:10.1142/s219688882250021x","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s219688882250021x","pdf_url":null,"source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1142/s219688882250021x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065382046","display_name":"An-Vinh Luong","orcid":"https://orcid.org/0000-0002-0754-7995"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"An-Vinh Luong","raw_affiliation_strings":["Computational Linguistics Center, University of Science, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics Center, University of Science, Ho Chi Minh City, Vietnam","institution_ids":[]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040236875","display_name":"\u0110i\u1ec1n \u0110inh","orcid":"https://orcid.org/0000-0003-2069-1016"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dien Dinh","raw_affiliation_strings":["Computational Linguistics Center, University of Science, Ho Chi Minh City, Vietnam","Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Linguistics Center, University of Science, Ho Chi Minh City, Vietnam","institution_ids":[]},{"raw_affiliation_string":"Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065382046"],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":0.1387,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54635047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"09","issue":"04","first_page":"395","last_page":"415"},"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":0.9830999970436096,"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/readability","display_name":"Readability","score":0.9624811410903931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8694572448730469},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7972004413604736},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.771355390548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6775890588760376},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.4918663501739502},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4751046597957611},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4686203598976135},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.4273521602153778},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4272298514842987},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.41094741225242615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37065398693084717},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31950944662094116},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21221914887428284}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9624811410903931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8694572448730469},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7972004413604736},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.771355390548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6775890588760376},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4918663501739502},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4751046597957611},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4686203598976135},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.4273521602153778},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4272298514842987},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.41094741225242615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37065398693084717},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31950944662094116},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21221914887428284},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s219688882250021x","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s219688882250021x","pdf_url":null,"source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:291d3262a2db4d0b8504b7dcd158d80e","is_oa":true,"landing_page_url":"https://doaj.org/article/291d3262a2db4d0b8504b7dcd158d80e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vietnam Journal of Computer Science, Vol 09, Iss 04, Pp 395-415 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1142/s219688882250021x","is_oa":true,"landing_page_url":"https://doi.org/10.1142/s219688882250021x","pdf_url":null,"source":{"id":"https://openalex.org/S2486636169","display_name":"Vietnam Journal of Computer Science","issn_l":"2196-8888","issn":["2196-8888","2196-8896"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vietnam Journal of Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W20138697","https://openalex.org/W1876710841","https://openalex.org/W1968078483","https://openalex.org/W2000332471","https://openalex.org/W2019416425","https://openalex.org/W2041304295","https://openalex.org/W2074703312","https://openalex.org/W2086874233","https://openalex.org/W2089975905","https://openalex.org/W2095507137","https://openalex.org/W2115968643","https://openalex.org/W2138200957","https://openalex.org/W2168523693","https://openalex.org/W2250496306","https://openalex.org/W2373203528","https://openalex.org/W2514166524","https://openalex.org/W2760797156","https://openalex.org/W2767726235","https://openalex.org/W2770352485","https://openalex.org/W2806183494","https://openalex.org/W2910594242","https://openalex.org/W2912908151","https://openalex.org/W2953626312"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2032810564","https://openalex.org/W210117510","https://openalex.org/W2006627376","https://openalex.org/W1769291553","https://openalex.org/W3099325276","https://openalex.org/W4214823418","https://openalex.org/W563979812"],"abstract_inverted_index":{"Text":[0],"readability":[1,17,42,85,104],"is":[2,11,59,131],"a":[3,14,20,45,76,81],"measure":[4],"of":[5,26,35,96,119,126,153,173],"how":[6],"easy":[7],"or":[8],"difficult":[9],"it":[10,165],"to":[12,79,170],"read":[13],"text.":[15],"This":[16,91],"factor":[18],"plays":[19],"crucial":[21],"role":[22],"in":[23,47,66,128,162],"the":[24,30,33,88,94,102,106,123,129,151,171],"processes":[25],"drafting":[27],"and":[28,54],"comprehending":[29],"texts,":[31],"affecting":[32],"choice":[34],"proper":[36],"texts":[37],"for":[38,52,83,87],"reading.":[39],"While":[40],"text":[41,84],"has":[43],"been":[44,110],"focus":[46],"research":[48],"on":[49,63,100,137,158],"computational":[50],"linguistics":[51],"English":[53],"other":[55,138,174],"resource-rich":[56],"languages,":[57],"there":[58],"still":[60],"little":[61],"work":[62],"this":[64,72],"subject":[65],"understudied":[67],"languages":[68,176],"like":[69],"Vietnamese.":[70],"In":[71],"study,":[73],"we":[74],"propose":[75],"semi-automated":[77],"method":[78,92,146],"build":[80],"corpus":[82,130,140],"purposes":[86],"Vietnamese":[89],"language.":[90],"performs":[93],"classification":[95,124],"new":[97],"documents":[98,107,127],"based":[99],"comparing":[101],"correlation":[103],"with":[105],"that":[108,122,143,155],"have":[109],"manually":[111],"pre-assessed":[112],"by":[113],"language":[114],"experts.":[115],"The":[116,134],"evaluation":[117],"results":[118,136],"experts":[120],"show":[121,142],"accuracy":[125],"over":[132],"90%.":[133],"experimental":[135],"available":[139],"also":[141,167],"our":[144],"proposed":[145],"can":[147,166],"not":[148],"only":[149],"address":[150],"lack":[152],"corpora":[154],"are":[156],"graded":[157],"various":[159],"difficulty":[160],"levels":[161],"Vietnamese,":[163],"but":[164],"be":[168],"extended":[169],"analysis":[172],"resource-poor":[175],"without":[177],"requiring":[178],"major":[179],"adjustments.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
