{"id":"https://openalex.org/W4205200734","doi":"https://doi.org/10.1109/rivf51545.2021.9642108","title":"Mining Japanese-Vietnamese multi-level parallel text corpus from Wikipedia data resource","display_name":"Mining Japanese-Vietnamese multi-level parallel text corpus from Wikipedia data resource","publication_year":2021,"publication_date":"2021-08-19","ids":{"openalex":"https://openalex.org/W4205200734","doi":"https://doi.org/10.1109/rivf51545.2021.9642108"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642108","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"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/A5061663230","display_name":"Thi-Ngoc-Diep Do","orcid":"https://orcid.org/0000-0001-9197-7850"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Thi-Ngoc-Diep Do","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Viet Nam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061663230"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":57},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9985,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9778,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.8475855},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.45004117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85567224},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8475855},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7742617},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.60706705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.59352183},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.58996},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5386268},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4876901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47974432},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.45004117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34465173},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11988357},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf51545.2021.9642108","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.71,"display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W107601741","https://openalex.org/W1249771036","https://openalex.org/W14574270","https://openalex.org/W1489181569","https://openalex.org/W1753482797","https://openalex.org/W191409295","https://openalex.org/W1973152633","https://openalex.org/W2006969979","https://openalex.org/W2014516359","https://openalex.org/W2047295649","https://openalex.org/W2104103102","https://openalex.org/W2107695330","https://openalex.org/W2130919220","https://openalex.org/W2159872955","https://openalex.org/W2250489405","https://openalex.org/W2251249103","https://openalex.org/W2251828955","https://openalex.org/W2275683873","https://openalex.org/W2324186081","https://openalex.org/W2335061175","https://openalex.org/W2341326075","https://openalex.org/W2407127455","https://openalex.org/W2588710172","https://openalex.org/W2736790173","https://openalex.org/W2962789428","https://openalex.org/W2998485758","https://openalex.org/W3208719332","https://openalex.org/W4241645538","https://openalex.org/W4288284086","https://openalex.org/W4298857067"],"related_works":["https://openalex.org/W4293584592","https://openalex.org/W4287212313","https://openalex.org/W3175595715","https://openalex.org/W3155572818","https://openalex.org/W3120880016","https://openalex.org/W2986030184","https://openalex.org/W2985215540","https://openalex.org/W2807849360","https://openalex.org/W2786253471","https://openalex.org/W2104907655"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,34,56,82,87,100,126],"task":[4],"of":[5,20,89,102,111,117],"mining":[6],"a":[7],"Japanese":[8],"-":[9],"Vietnamese":[10,77],"parallel":[11,35,91,96,112,118],"text":[12,36,97],"corpus":[13],"from":[14],"comparable":[15],"data":[16,52],"resources":[17],"in":[18],"application":[19],"machine":[21,103],"translation.":[22],"Data":[23],"resource":[24,79],"for":[25],"this":[26],"language":[27,70],"pair":[28],"is":[29],"few":[30],"and":[31,45,114,123],"rare":[32],"so":[33,63],"should":[37],"be":[38,66],"extracted":[39,90,94],"at":[40],"multi":[41],"levels,":[42],"sentence":[43],"level":[44],"fragment":[46],"level,":[47],"to":[48,68,99,125],"get":[49],"as":[50,53,105],"much":[51],"possible.":[54],"Moreover,":[55],"proposed":[57,83],"method":[58,84],"considers":[59],"word":[60],"order":[61],"independently":[62],"it":[64],"can":[65],"applied":[67,74],"different":[69],"families.":[71],"The":[72,93],"result":[73],"on":[75],"Japanese-":[76],"Wikipedia":[78],"shows":[80],"that":[81],"increases":[85],"significantly":[86],"number":[88],"data.":[92],"multi-level":[95],"contributes":[98],"quality":[101],"translation":[104],"well.":[106],"More":[107],"than":[108],"144,000":[109],"pairs":[110,116],"sentences":[113],"148,000":[115],"fragments":[119],"had":[120],"been":[121],"mined":[122],"opened":[124],"research":[127],"community.":[128]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4205200734","counts_by_year":[],"updated_date":"2024-12-10T07:03:10.287465","created_date":"2022-01-26"}