{"id":"https://openalex.org/W2550455130","doi":"https://doi.org/10.1145/2988237","title":"Word Re-Segmentation in Chinese-Vietnamese Machine Translation","display_name":"Word Re-Segmentation in Chinese-Vietnamese Machine Translation","publication_year":2016,"publication_date":"2016-11-04","ids":{"openalex":"https://openalex.org/W2550455130","doi":"https://doi.org/10.1145/2988237","mag":"2550455130"},"language":"en","primary_location":{"id":"doi:10.1145/2988237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2988237","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5103075904","display_name":"Phuoc Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I141445968","display_name":"Ton Duc Thang University","ror":"https://ror.org/01drq0835","country_code":"VN","type":"education","lineage":["https://openalex.org/I141445968"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuoc Tran","raw_affiliation_strings":["Ton Duc Thang University, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ton Duc Thang University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I141445968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040236875","display_name":"\u0110i\u1ec1n \u0110inh","orcid":"https://orcid.org/0000-0003-2069-1016"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"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":"Dien Dinh","raw_affiliation_strings":["VNU University of Science, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I67868205"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048517713","display_name":"Long Nguyen","orcid":"https://orcid.org/0000-0002-0884-1635"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]},{"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":"Long H. B. Nguyen","raw_affiliation_strings":["VNU University of Science, Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNU University of Science, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I23582244","https://openalex.org/I67868205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2993,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87446791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"22"},"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":0.9987999796867371,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9839000105857849,"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":0.8738411664962769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8278225660324097},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.8224468231201172},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7615783214569092},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.6981823444366455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6688859462738037},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6271554231643677},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5778762102127075},{"id":"https://openalex.org/keywords/computer-assisted-translation","display_name":"Computer-assisted translation","score":0.5341073274612427},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5234853029251099},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4961734712123871},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.49553215503692627},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.49136796593666077},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.4715716242790222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4507265090942383},{"id":"https://openalex.org/keywords/synchronous-context-free-grammar","display_name":"Synchronous context-free grammar","score":0.43394798040390015},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.2896603047847748},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21294769644737244}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8738411664962769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278225660324097},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8224468231201172},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7615783214569092},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.6981823444366455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6688859462738037},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6271554231643677},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5778762102127075},{"id":"https://openalex.org/C110046852","wikidata":"https://www.wikidata.org/wiki/Q468495","display_name":"Computer-assisted translation","level":3,"score":0.5341073274612427},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5234853029251099},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4961734712123871},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.49553215503692627},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.49136796593666077},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4715716242790222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4507265090942383},{"id":"https://openalex.org/C51802942","wikidata":"https://www.wikidata.org/wiki/Q7662211","display_name":"Synchronous context-free grammar","level":4,"score":0.43394798040390015},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2896603047847748},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21294769644737244},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2988237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2988237","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W61894391","https://openalex.org/W1412698887","https://openalex.org/W1591201057","https://openalex.org/W2017802499","https://openalex.org/W2057200159","https://openalex.org/W2095907708","https://openalex.org/W2117400858","https://openalex.org/W2129400979","https://openalex.org/W2131988669","https://openalex.org/W2144783305","https://openalex.org/W2147880316","https://openalex.org/W2157435188","https://openalex.org/W2162465526","https://openalex.org/W2164766438","https://openalex.org/W2170464899","https://openalex.org/W2188581170","https://openalex.org/W2251066033","https://openalex.org/W2251536071","https://openalex.org/W2407949352","https://openalex.org/W2496334041","https://openalex.org/W2787109023","https://openalex.org/W2998314454","https://openalex.org/W3127744049","https://openalex.org/W3167119764"],"related_works":["https://openalex.org/W3204448004","https://openalex.org/W2566847733","https://openalex.org/W2596454883","https://openalex.org/W4321010057","https://openalex.org/W2122287718","https://openalex.org/W2407077619","https://openalex.org/W2740094425","https://openalex.org/W4312364893","https://openalex.org/W2587602790","https://openalex.org/W2520395186"],"abstract_inverted_index":{"In":[0,99],"isolated":[1,116],"languages,":[2],"such":[3],"as":[4],"Chinese":[5,109],"and":[6,14,46,55,76,84,110,114,121,138,184],"Vietnamese,":[7],"words":[8],"are":[9,72],"not":[10,59,73],"separated":[11],"by":[12,20],"spaces,":[13],"a":[15],"word":[16,26,78,124],"may":[17,58],"be":[18,60],"formed":[19],"one":[21],"or":[22],"more":[23,130],"syllables.":[24],"Therefore,":[25,63],"segmentation":[27],"(WS)":[28],"is":[29,35,49],"usually":[30],"the":[31,38,44,61,64,94,105,123,127,149,170,177],"first":[32],"process":[33],"that":[34,66,164],"implemented":[36],"in":[37,43,68,81,88,112,119,132],"machine":[39,90,97,140,173],"translation":[40,141,174,179,182,188],"process.":[41],"WS":[42,56,65,106,181,187],"source":[45],"target":[47],"languages":[48,71,129],"based":[50],"on":[51,148],"different":[52],"training":[53],"corpora,":[54],"approaches":[57],"same.":[62],"results":[67,80,162],"these":[69],"two":[70,128],"often":[74],"homologous,":[75],"thus":[77],"alignment":[79,86],"many":[82],"1-n":[83],"n-1":[85],"pairs":[87,118],"statistical":[89],"translation,":[91],"which":[92,154],"degrades":[93],"performance":[95,171],"of":[96,126,156,172],"translation.":[98],"this":[100,146],"article,":[101],"we":[102],"will":[103],"adjust":[104],"for":[107,115],"both":[108],"Vietnamese":[111],"particular":[113],"language":[117],"general":[120],"make":[122],"boundary":[125],"symmetric":[131],"order":[133],"to":[134,176],"strengthen":[135],"1-1":[136],"alignments":[137],"enhance":[139],"performance.":[142],"We":[143],"have":[144],"tested":[145],"method":[147,166],"Computational":[150],"Linguistics":[151],"Center\u2019s":[152],"corpus,":[153],"consists":[155],"35,623":[157],"sentence":[158],"pairs.":[159],"The":[160],"experimental":[161],"show":[163],"our":[165],"has":[167],"significantly":[168],"improved":[169],"compared":[175],"baseline":[178],"system,":[180,183],"anchor":[185],"language-based":[186],"systems.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
