{"id":"https://openalex.org/W6910543787","doi":"https://doi.org/10.48550/arxiv.2310.05381","title":"CCAE: A Corpus of Chinese-based Asian Englishes","display_name":"CCAE: A Corpus of Chinese-based Asian Englishes","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W6910543787","doi":"https://doi.org/10.48550/arxiv.2310.05381"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2310.05381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2310.05381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liu, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qin, Melissa Xiaohui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Melissa Xiaohui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Long","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Huang, Chao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.34450000524520874,"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":0.34450000524520874,"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":0.12919999659061432,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.12290000170469284,"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/variety","display_name":"Variety (cybernetics)","score":0.602400004863739},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.489300012588501},{"id":"https://openalex.org/keywords/world-englishes","display_name":"World Englishes","score":0.4424999952316284},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.3709000051021576},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7141000032424927},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5945000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889000296592712},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5364999771118164},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2776331648","wikidata":"https://www.wikidata.org/wiki/Q3545554","display_name":"World Englishes","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.32089999318122864},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.2800000011920929}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2310.05381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2310.05381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.618432343006134}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language":[0],"models":[1],"have":[2],"been":[3,15,125],"foundations":[4],"in":[5,18,44,51,90],"various":[6],"scenarios":[7],"of":[8,34,47,64,69,75,100,163],"NLP":[9,42],"applications,":[10],"but":[11],"it":[12],"has":[13,123],"not":[14,124],"well":[16],"applied":[17],"language":[19,27,139],"variety":[20],"studies,":[21],"even":[22],"for":[23,56,113,117,120,137,148],"the":[24,35,41,45,65,104,146,160],"most":[25],"popular":[26],"like":[28],"English.":[29],"This":[30],"paper":[31],"represents":[32],"one":[33],"few":[36],"initial":[37],"efforts":[38],"to":[39],"utilize":[40],"technology":[43],"paradigm":[46],"World":[48,150],"Englishes,":[49],"specifically":[50],"creating":[52],"a":[53,73,106,126],"multi-variety":[54],"corpus":[55,105,129,158],"studying":[57],"Asian":[58,71,80,114],"Englishes.":[59],"We":[60],"present":[61],"an":[62,134],"overview":[63],"CCAE":[66,168],"--":[67],"Corpus":[68],"Chinese-based":[70,79],"English,":[72],"suite":[74],"corpora":[76],"comprising":[77],"six":[78,96],"English":[81],"varieties.":[82],"It":[83],"is":[84],"based":[85],"on":[86,156],"340":[87],"million":[88],"tokens":[89],"448":[91],"thousand":[92],"web":[93],"documents":[94],"from":[95],"regions.":[97],"The":[98],"ontology":[99],"data":[101],"would":[102],"make":[103,167],"helpful":[107],"resource":[108],"with":[109],"enormous":[110],"research":[111],"potential":[112],"Englishes":[115,119,151],"(especially":[116],"Chinese":[118],"which":[121],"there":[122],"publicly":[127],"accessible":[128],"yet":[130],"so":[131],"far)":[132],"and":[133,141],"ideal":[135],"source":[136],"variety-specific":[138],"modeling":[140],"downstream":[142],"tasks,":[143],"thus":[144],"setting":[145],"stage":[147],"NLP-based":[149],"studies.":[152],"And":[153],"preliminary":[154],"experiments":[155],"this":[157],"reveal":[159],"practical":[161],"value":[162],"CCAE.":[164],"Finally,":[165],"we":[166],"available":[169],"at":[170],"\\href{https://huggingface.co/datasets/CCAE/CCAE-Corpus}{this":[171],"https":[172],"URL}.":[173]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
