{"id":"https://openalex.org/W4399464853","doi":"https://doi.org/10.1007/s10579-024-09744-w","title":"Cantonese natural language processing in the transformers era: a survey and current challenges","display_name":"Cantonese natural language processing in the transformers era: a survey and current challenges","publication_year":2024,"publication_date":"2024-06-08","ids":{"openalex":"https://openalex.org/W4399464853","doi":"https://doi.org/10.1007/s10579-024-09744-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-024-09744-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09744-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09744-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09744-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049550908","display_name":"Rong Xiang","orcid":"https://orcid.org/0000-0001-7560-1378"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Rong Xiang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079921667","display_name":"Emmanuele Chersoni","orcid":"https://orcid.org/0000-0001-8742-0451"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Emmanuele Chersoni","raw_affiliation_strings":["Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108323276","display_name":"Yixia Li","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yixia Li","raw_affiliation_strings":["Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China","Department of Intelligent Science, Xi-an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Intelligent Science, Xi-an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683634","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-6652-6000"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024924150","display_name":"Chu\u2010Ren Huang","orcid":"https://orcid.org/0000-0002-8526-5520"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chu-Ren Huang","raw_affiliation_strings":["Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044105477","display_name":"Yushan Pan","orcid":"https://orcid.org/0000-0002-6877-3937"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushan Pan","raw_affiliation_strings":["Department of Computing, Xi-an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Xi-an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108280727","display_name":"Y. C. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yushi Li","raw_affiliation_strings":["Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China","Department of Intelligent Science, Xi-an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Intelligent Science, Xi-an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079921667"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":1.2151,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8157703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"59","issue":"2","first_page":"1747","last_page":"1773"},"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6814901828765869},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5657711029052734},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4962220788002014},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4077168107032776},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39164042472839355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.354254812002182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16864827275276184},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1104544997215271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814901828765869},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5657711029052734},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4962220788002014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4077168107032776},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39164042472839355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.354254812002182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16864827275276184},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1104544997215271},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10579-024-09744-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09744-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09744-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/108877","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/108877","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/108877/1/s10579-024-09744-w.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"doi:10.1007/s10579-024-09744-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09744-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09744-w.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8799999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399464853.pdf"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W166789335","https://openalex.org/W648225809","https://openalex.org/W656085213","https://openalex.org/W1964157370","https://openalex.org/W1982957697","https://openalex.org/W1986585666","https://openalex.org/W2001569578","https://openalex.org/W2013380941","https://openalex.org/W2025000088","https://openalex.org/W2041284809","https://openalex.org/W2054125330","https://openalex.org/W2069245580","https://openalex.org/W2161490380","https://openalex.org/W2164418233","https://openalex.org/W2165691108","https://openalex.org/W2251892835","https://openalex.org/W2275660037","https://openalex.org/W2280955656","https://openalex.org/W2399715921","https://openalex.org/W2512700785","https://openalex.org/W2578036461","https://openalex.org/W2690082738","https://openalex.org/W2745590170","https://openalex.org/W2797438418","https://openalex.org/W2805499166","https://openalex.org/W2892131163","https://openalex.org/W2915977242","https://openalex.org/W2923014074","https://openalex.org/W2933762913","https://openalex.org/W2943552823","https://openalex.org/W2945106857","https://openalex.org/W2952335829","https://openalex.org/W2952370363","https://openalex.org/W2952638691","https://openalex.org/W2970419734","https://openalex.org/W2970480900","https://openalex.org/W2971296908","https://openalex.org/W2990138404","https://openalex.org/W2995847235","https://openalex.org/W3001434439","https://openalex.org/W3020872323","https://openalex.org/W3024308166","https://openalex.org/W3034775979","https://openalex.org/W3035352537","https://openalex.org/W3035390927","https://openalex.org/W3101948613","https://openalex.org/W3104186312","https://openalex.org/W3111054085","https://openalex.org/W3113798072","https://openalex.org/W3156636935","https://openalex.org/W3161110574","https://openalex.org/W3169754410","https://openalex.org/W3171355829","https://openalex.org/W3173780338","https://openalex.org/W3176398418","https://openalex.org/W3185269176","https://openalex.org/W3199962080","https://openalex.org/W3210565818","https://openalex.org/W4241566960","https://openalex.org/W4242346149","https://openalex.org/W4248862027","https://openalex.org/W4280654130","https://openalex.org/W4285224078","https://openalex.org/W4285225959","https://openalex.org/W4287890953","https://openalex.org/W4299513722","https://openalex.org/W4300445512","https://openalex.org/W4386576675","https://openalex.org/W4391136507","https://openalex.org/W4392669753","https://openalex.org/W4404784144","https://openalex.org/W4408331781","https://openalex.org/W4409093533","https://openalex.org/W6600339963","https://openalex.org/W6602752192","https://openalex.org/W6607919353","https://openalex.org/W6630240118","https://openalex.org/W6694249425","https://openalex.org/W6750279369","https://openalex.org/W6778584705","https://openalex.org/W6778597757","https://openalex.org/W6809982797","https://openalex.org/W6890425945","https://openalex.org/W7037943041","https://openalex.org/W7070571517"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W3204019825","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"being":[2],"spoken":[3],"by":[4,42],"a":[5,50],"large":[6],"population":[7],"of":[8,16,75,83],"speakers":[9],"worldwide,":[10],"Cantonese":[11,60,85],"is":[12,40],"under-resourced":[13],"in":[14,68],"terms":[15],"the":[17,33,54,65,84],"data":[18],"scale":[19],"and":[20,36,57,73,98],"diversity":[21],"compared":[22],"to":[23],"other":[24],"major":[25],"languages.":[26],"This":[27],"limitation":[28],"has":[29],"excluded":[30],"it":[31,90],"from":[32],"current":[34],"\u201cpre-training":[35],"fine-tuning\u201d":[37],"paradigm":[38],"that":[39,87],"dominated":[41],"Transformer":[43],"architectures.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"provide":[49],"comprehensive":[51],"review":[52],"on":[53],"existing":[55],"resources":[56],"methodologies":[58],"for":[59,94],"Natural":[61],"Language":[62],"Processing,":[63],"covering":[64],"recent":[66],"progress":[67],"language":[69,76,86],"understanding,":[70],"text":[71],"generation":[72],"development":[74],"models.":[77],"We":[78],"finally":[79],"discuss":[80],"two":[81],"aspects":[82],"could":[88],"make":[89],"potentially":[91],"challenging":[92],"even":[93],"state-of-the-art":[95],"architectures:":[96],"colloquialism":[97],"multilinguality":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}