{"id":"https://openalex.org/W4226360463","doi":"https://doi.org/10.1145/3508230.3508242","title":"Low-Resource NMT: A Case Study on the Written and Spoken Languages in Hong Kong","display_name":"Low-Resource NMT: A Case Study on the Written and Spoken Languages in Hong Kong","publication_year":2021,"publication_date":"2021-12-17","ids":{"openalex":"https://openalex.org/W4226360463","doi":"https://doi.org/10.1145/3508230.3508242"},"language":"en","primary_location":{"id":"doi:10.1145/3508230.3508242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508230.3508242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR)","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/A5085639863","display_name":"Hei Yi Mak","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hei Yi Mak","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.4095,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70091435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9818000197410583,"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":0.9520999789237976,"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/computer-science","display_name":"Computer science","score":0.7852625846862793},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7043184638023376},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6713996529579163},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6143598556518555},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6049638390541077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5855721831321716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.53008633852005},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46213191747665405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3319139778614044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852625846862793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7043184638023376},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6713996529579163},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6143598556518555},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6049638390541077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5855721831321716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.53008633852005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46213191747665405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3319139778614044},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3508230.3508242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508230.3508242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Natural Language Processing and Information Retrieval (NLPIR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W656085213","https://openalex.org/W1490960179","https://openalex.org/W1976955713","https://openalex.org/W2130942839","https://openalex.org/W2251892835","https://openalex.org/W2524182563","https://openalex.org/W2613904329","https://openalex.org/W2905749056","https://openalex.org/W2917458986","https://openalex.org/W4391156274"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2903399267","https://openalex.org/W2949454572","https://openalex.org/W2952599318","https://openalex.org/W2890256614"],"abstract_inverted_index":{"The":[0,53,65],"majority":[1],"of":[2,55,105,115,122,126,160,201],"inhabitants":[3],"in":[4,13,24,61,187,205],"Hong":[5],"Kong":[6],"are":[7,109],"able":[8,215],"to":[9,76,133,151,216],"read":[10],"and":[11,46,71,85,107,142,170,224],"write":[12],"standard":[14,50,222],"Chinese":[15,33,84,106,168,223],"but":[16],"use":[17],"Cantonese":[18,28,42,57,72,108,171],"as":[19],"the":[20,37,62,120],"primary":[21],"spoken":[22,225],"language":[23],"daily":[25],"life.":[26],"Spoken":[27],"can":[29],"be":[30],"transcribed":[31],"into":[32],"characters,":[34],"which":[35],"constitute":[36],"so-called":[38],"written":[39,51,56],"Cantonese.":[40,86,226],"Written":[41],"exhibits":[43],"significant":[44],"lexical":[45],"grammatical":[47],"differences":[48],"from":[49,138,164,182],"Chinese.":[52],"rise":[54],"is":[58,74,118,214],"increasingly":[59],"evident":[60],"cyber":[63],"world.":[64],"growing":[66],"interaction":[67],"between":[68,83,221],"Mandarin":[69],"speakers":[70,73],"leading":[75],"a":[77,90,112],"clear":[78],"demand":[79],"for":[80,97,129],"automatic":[81],"translation":[82,94,185,197],"This":[87],"paper":[88],"describes":[89],"transformer-based":[91],"neural":[92],"machine":[93],"(NMT)":[95],"system":[96,192,213],"written-Chinese-to-written-Cantonese":[98],"translation.":[99],"Given":[100],"that":[101,175,211],"parallel":[102,136,154,165],"text":[103],"data":[104,128],"extremely":[110],"scarce,":[111],"major":[113],"focus":[114],"this":[116],"study":[117],"on":[119,167,198],"effort":[121],"preparing":[123],"good":[124],"amount":[125],"training":[127],"NMT.":[130],"In":[131],"addition":[132],"collecting":[134],"28K":[135],"sentences":[137,155,163],"previous":[139],"linguistic":[140,219],"studies":[141],"scattered":[143],"internet":[144],"resources,":[145],"we":[146],"devise":[147],"an":[148],"effective":[149],"approach":[150],"obtaining":[152],"72K":[153],"by":[156],"automatically":[157],"extracting":[158],"pairs":[159,180],"semantically":[161],"similar":[162,178],"articles":[166],"Wikipedia":[169,183],"Wikipedia.":[172],"We":[173],"show":[174],"leveraging":[176],"highly":[177],"sentence":[179],"mined":[181],"improves":[184],"performance":[186],"all":[188],"test":[189,203],"sets.":[190],"Our":[191],"outperforms":[193],"Baidu":[194],"Fanyi's":[195],"Chinese-to-Cantonese":[196],"6":[199],"out":[200],"8":[202],"sets":[204],"BLEU":[206],"scores.":[207],"Translation":[208],"examples":[209],"reveal":[210],"our":[212],"capture":[217],"important":[218],"transformations":[220]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}