{"id":"https://openalex.org/W4392445543","doi":"https://doi.org/10.1145/3639233.3639332","title":"Cantonese to Written Chinese Translation via HuggingFace Translation Pipeline","display_name":"Cantonese to Written Chinese Translation via HuggingFace Translation Pipeline","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4392445543","doi":"https://doi.org/10.1145/3639233.3639332"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639332","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103260119","display_name":"Raptor Yick-Kan Kwok","orcid":"https://orcid.org/0000-0001-5683-968X"},"institutions":[],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Raptor Yick-Kan Kwok","raw_affiliation_strings":["School of Science and Technology, Hong Kong Metropolitan University, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045211387","display_name":"Siu-Kei Au Yeung","orcid":"https://orcid.org/0000-0001-6523-9547"},"institutions":[],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siu-Kei Au Yeung","raw_affiliation_strings":["School of Science and Technology, Hong Kong Metropolitan University, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076059022","display_name":"Zongxi Li","orcid":"https://orcid.org/0000-0002-1708-7099"},"institutions":[],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongxi Li","raw_affiliation_strings":["School of Science and Technology, Hong Kong Metropolitan University, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051376589","display_name":"Kevin Hung","orcid":"https://orcid.org/0000-0002-5421-7622"},"institutions":[],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kevin Hung","raw_affiliation_strings":["School of Science and Technology, Hong Kong Metropolitan University, China"],"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Hong Kong Metropolitan University, China","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"fulltext_origin":"pdf","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":68},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"84"},"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":0.9998,"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":0.9951,"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/bleu","display_name":"BLEU","score":0.77927905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80460167},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.77927905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.76622415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636268},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6402968},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.635967},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5060105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35990357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639332","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639233.3639332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639233.3639332","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.48}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":10,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2250342921","https://openalex.org/W2758950307","https://openalex.org/W2963532001","https://openalex.org/W2979826702","https://openalex.org/W3100806282","https://openalex.org/W4226360463","https://openalex.org/W4288088047","https://openalex.org/W656085213"],"related_works":["https://openalex.org/W4280571180","https://openalex.org/W3066373881","https://openalex.org/W3021126373","https://openalex.org/W2903057408","https://openalex.org/W2807475932","https://openalex.org/W2518299649","https://openalex.org/W2426188458","https://openalex.org/W2395641992","https://openalex.org/W2099607809","https://openalex.org/W1915251500"],"abstract_inverted_index":{"Cantonese,":[0],"a":[1,44,62,75,97,126,152],"low-resource":[2],"language":[3,29,80],"[5]":[4],"that":[5,184,203],"has":[6],"been":[7],"used":[8,59],"in":[9,26],"Southeastern":[10],"China":[11],"for":[12,31,78],"hundreds":[13],"of":[14,48,69,100,104,119,129,133,161,189,211],"years,":[15],"with":[16,116,141,177],"over":[17,120],"85":[18],"million":[19],"native":[20],"speakers":[21],"worldwide,":[22],"is":[23],"poorly":[24],"supported":[25],"the":[27,66,70,91,106,142,159,162,172,178,185,187,190,193,195,207,212],"mainstream":[28],"model":[30,64,111],"existing":[32,143],"translation":[33,63,67,94,209],"platforms":[34],"such":[35],"as":[36],"Baidu,":[37],"Google":[38],"and":[39,52,87,146,174,182,197],"Bing.":[40],"This":[41],"paper":[42],"presents":[43],"large":[45],"parallel":[46],"corpus":[47,205],"130":[49],"thousand":[50],"Cantonese":[51,153,164,208],"Written":[53],"Chinese":[54,122,213],"pairs.":[55],"The":[56,84,93,110],"data":[57],"are":[58,139],"to":[60,157],"train":[61],"using":[65],"pipeline":[68],"Hugging":[71],"Face":[72],"Transformers":[73],"architecture,":[74],"dominant":[76],"architecture":[77],"natural":[79],"processing":[81],"nowadays":[82],"[18].":[83],"BLEU":[85,98,127,173,196],"score":[86,99,103,128,132,181],"manual":[88],"assessment":[89],"evaluate":[90],"performance.":[92],"results":[95,138],"achieve":[96],"41.35and":[101],"chrF++":[102,131,175,198],"44.88on":[105],"entire":[107],"validation":[108],"set.":[109],"also":[112,150],"works":[113],"reasonably":[114],"well":[115],"long":[117,135],"sentences":[118],"20":[121],"characters.":[123],"It":[124],"achieves":[125],"48.61and":[130],"39.87on":[134],"sentences.":[136],"Those":[137],"comparable":[140],"Baidu":[144],"Fanyi":[145],"Bing":[147],"Translate.":[148],"We":[149,169],"establish":[151],"sentence":[154,165],"evaluation":[155,180],"metric":[156],"classify":[158],"quality":[160,188],"source":[163,191],"by":[166],"professional":[167],"translators.":[168],"then":[170],"compare":[171],"scores":[176],"corresponding":[179],"found":[183],"better":[186],"sentence,":[192],"higher":[194],"scores.":[199],"Last,":[200],"we":[201],"proved":[202],"our":[204],"enabled":[206],"capability":[210],"BART":[214],"pre-trained":[215],"model.":[216]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4392445543","counts_by_year":[],"updated_date":"2024-12-10T11:58:05.571958","created_date":"2024-03-06"}