{"id":"https://openalex.org/W2946027757","doi":"https://doi.org/10.1109/rivf.2019.8713737","title":"Long Sentence Preprocessing in Neural Machine Translation","display_name":"Long Sentence Preprocessing in Neural Machine Translation","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2946027757","doi":"https://doi.org/10.1109/rivf.2019.8713737","mag":"2946027757"},"language":"en","primary_location":{"id":"doi:10.1109/rivf.2019.8713737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"},"type":"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/A5088290760","display_name":"Ha Nguyen Tien","orcid":null},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ha Nguyen Tien","raw_affiliation_strings":["Faculty of Mathematics, Mechanics and Informatics, VNU University of Science, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Mechanics and Informatics, VNU University of Science, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091696309","display_name":"Huy\u1ec1n Nguy\u1ec5n Th\u1ecb Minh","orcid":null},"institutions":[{"id":"https://openalex.org/I67868205","display_name":"VNU University of Science","ror":"https://ror.org/05w54hk79","country_code":"VN","type":"education","lineage":["https://openalex.org/I177233841","https://openalex.org/I67868205"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huyen Nguyen Thi Minh","raw_affiliation_strings":["Faculty of Mathematics, Mechanics and Informatics, VNU University of Science, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Mathematics, Mechanics and Informatics, VNU University of Science, Hanoi, Vietnam","institution_ids":["https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67868205"],"apc_list":null,"apc_paid":null,"fwci":0.8678,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80575352,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":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":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/machine-translation","display_name":"Machine translation","score":0.8544981479644775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141525387763977},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6191218495368958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5988183617591858},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5786832571029663},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5713163614273071},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5022037029266357},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4909806549549103},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.4491908848285675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4001845121383667}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8544981479644775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141525387763977},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6191218495368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5988183617591858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5786832571029663},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5713163614273071},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5022037029266357},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4909806549549103},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.4491908848285675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4001845121383667},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf.2019.8713737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W132913264","https://openalex.org/W1902237438","https://openalex.org/W2004326952","https://openalex.org/W2124807415","https://openalex.org/W2133564696","https://openalex.org/W2143927888","https://openalex.org/W2167662847","https://openalex.org/W2418190651","https://openalex.org/W2525778437","https://openalex.org/W2540060078","https://openalex.org/W2558155472","https://openalex.org/W2963212250","https://openalex.org/W2963506925","https://openalex.org/W2964335437","https://openalex.org/W6605403940"],"related_works":["https://openalex.org/W193726211","https://openalex.org/W1559710535","https://openalex.org/W2566847733","https://openalex.org/W2010336863","https://openalex.org/W2962780935","https://openalex.org/W3204448004","https://openalex.org/W4378619223","https://openalex.org/W2027317339","https://openalex.org/W2532807140","https://openalex.org/W2378657301"],"abstract_inverted_index":{"Machine":[0],"translation":[1,23,52,64,104,112],"based":[2],"on":[3],"neural":[4,21,62,102,110],"networks":[5],"has":[6],"been":[7],"shown":[8],"to":[9,29,78,82,97,114],"produce":[10],"superior":[11],"results,":[12],"compared":[13],"with":[14],"other":[15],"approaches.":[16],"To":[17],"build":[18,83],"an":[19,31,124],"efficient":[20],"machine":[22,103,111],"(NMT)":[24],"system,":[25],"it":[26],"is":[27,66],"essential":[28],"have":[30],"accurate":[32],"and":[33,39,47,88],"massive":[34],"bilingual":[35,80,86],"corpus":[36],"for":[37,60],"training,":[38],"ensure":[40],"the":[41,45,51,89,101,109],"continuous":[42],"improvement":[43,125],"of":[44,91,108],"methods":[46],"techniques":[48],"used":[49,99],"in":[50,100,126],"system.":[53],"Despite":[54],"multiple":[55],"advantages,":[56],"one":[57],"challenging":[58],"issue":[59],"current":[61],"network":[63],"system":[65,113],"long":[67,93],"sentence":[68,94],"processing":[69],"[1].":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"a":[76,84,92],"method":[77],"extract":[79],"phrases":[81],"phrase-aligned":[85],"corpus,":[87],"implementation":[90],"preprocessing":[95],"technique":[96,122],"be":[98],"model.":[105],"Experimental":[106],"training":[107],"translate":[115],"Vietnamese":[116],"into":[117],"English":[118],"using":[119],"our":[120],"proposed":[121],"shows":[123],"BLEU":[127],"scores.":[128]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
