{"id":"https://openalex.org/W4416036042","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.102","title":"Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models","display_name":"Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036042","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.102"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.102","pdf_url":"https://aclanthology.org/2025.findings-emnlp.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.102.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038913434","display_name":"Jiyue Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiyue Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065947249","display_name":"Alfred Kar Yin Truong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfred Kar Yin Truong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639362","display_name":"Yanyu Chen","orcid":"https://orcid.org/0000-0002-2275-6912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101286869","display_name":"Qinghang Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinghang Bao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371313","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-2696-2171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053263555","display_name":"Pengan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengan Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078001917","display_name":"Jiuming Wang","orcid":"https://orcid.org/0009-0003-9591-156X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiuming Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014554970","display_name":"Lingpeng Kong","orcid":"https://orcid.org/0000-0002-9033-2724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingpeng Kong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345915","display_name":"Yu Li","orcid":"https://orcid.org/0000-0003-1865-8276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012597518","display_name":"Chuan Wu","orcid":"https://orcid.org/0000-0002-3144-4398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1924","last_page":"1944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1843000054359436,"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/T10028","display_name":"Topic Modeling","score":0.1843000054359436,"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/T14347","display_name":"Big Data and Digital Economy","score":0.16249999403953552,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08889999985694885,"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/computational-linguistics","display_name":"Computational linguistics","score":0.36070001125335693},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3467999994754791},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.321399986743927},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.31619998812675476},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.30799999833106995}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6122000217437744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5679000020027161},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4066999852657318},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.302700012922287}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.102","pdf_url":"https://aclanthology.org/2025.findings-emnlp.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.102","pdf_url":"https://aclanthology.org/2025.findings-emnlp.102.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036042.pdf","grobid_xml":"https://content.openalex.org/works/W4416036042.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Jiyue":[0],"Jiang,":[1],"Alfred":[2],"Kar":[3],"Yin":[4],"Truong,":[5],"Yanyu":[6],"Chen,":[7,13],"Qinghang":[8],"Bao,":[9],"Sheng":[10],"Wang,":[11,15],"Pengan":[12],"Jiuming":[14],"Lingpeng":[16],"Kong,":[17],"Yu":[18],"Li,":[19],"Chuan":[20],"Wu.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"EMNLP":[29],"2025.":[30,31]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}
