{"id":"https://openalex.org/W4415110303","doi":"https://doi.org/10.18653/v1/2026.findings-acl.80","title":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","display_name":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415110303","doi":"https://doi.org/10.18653/v1/2026.findings-acl.80"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.80","pdf_url":"https://aclanthology.org/2026.findings-acl.80.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: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.80.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093939668","display_name":"Svetlana Churina","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Svetlana Churina","raw_affiliation_strings":["Centre for Trusted Internet & Community , National University of Singapore , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Trusted Internet & Community , National University of Singapore , Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112531","display_name":"Akshat Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Akshat Gupta","raw_affiliation_strings":["Centre for Trusted Internet & Community , National University of Singapore , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Trusted Internet & Community , National University of Singapore , Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118306985","display_name":"Insyirah Mujtahid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nur Insyirah Binte Imam Mujtahid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079154791","display_name":"Kokil Jaidka","orcid":"https://orcid.org/0000-0002-8127-1157"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kokil Jaidka","raw_affiliation_strings":["Centre for Trusted Internet & Community , National University of Singapore , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Trusted Internet & Community , National University of Singapore , Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01295919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1602","last_page":"1624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9897000193595886,"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/T13629","display_name":"Text Readability and Simplification","score":0.9897000193595886,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9319999814033508,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9211999773979187,"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/metadata","display_name":"Metadata","score":0.7207000255584717},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7073000073432922},{"id":"https://openalex.org/keywords/json","display_name":"JSON","score":0.6402999758720398},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.589900016784668},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.579200029373169},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5160999894142151},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.37770000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422000169754028},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7207000255584717},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7073000073432922},{"id":"https://openalex.org/C2780416260","wikidata":"https://www.wikidata.org/wiki/Q2063","display_name":"JSON","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5874999761581421},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49959999322891235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4339999854564667},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C2984865316","wikidata":"https://www.wikidata.org/wiki/Q25481968","display_name":"Speech act","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.80","pdf_url":"https://aclanthology.org/2026.findings-acl.80.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.00332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00332","pdf_url":"https://arxiv.org/pdf/2506.00332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.00332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.80","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.80","pdf_url":"https://aclanthology.org/2026.findings-acl.80.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4050478101","display_name":null,"funder_award_id":"MOE-MOET32022-0001","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415110303.pdf","grobid_xml":"https://content.openalex.org/works/W4415110303.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Code-mixing":[0],"involves":[1],"the":[2,56,93],"seamless":[3],"integration":[4],"of":[5,39],"linguistic":[6],"elements":[7],"from":[8],"multiple":[9],"languages":[10],"within":[11],"a":[12,37,83,99],"single":[13],"discourse,":[14],"reflecting":[15],"natural":[16],"multilingual":[17],"communication":[18],"patterns.Despite":[19],"its":[20],"prominence":[21],"in":[22,65,104],"informal":[23],"interactions":[24],"such":[25],"as":[26,98],"social":[27],"media,":[28],"chat":[29],"messages":[30,77],"and":[31,46,52,59,71,89,108,111],"instantmessaging":[32],"exchanges,":[33],"there":[34],"has":[35],"been":[36],"lack":[38],"publicly":[40],"available":[41],"corpora":[42],"that":[43],"are":[44],"authorlabeled":[45],"suitable":[47],"for":[48,62,102],"modeling":[49],"human":[50],"conversations":[51],"relationships.This":[53],"study":[54],"introduces":[55],"first":[57],"labeled":[58],"general-purpose":[60],"corpus":[61],"understanding":[63],"code-mixing":[64,80],"context":[66],"while":[67],"maintaining":[68],"rigorous":[69],"privacy":[70],"ethical":[72],"standards.It":[73],"includes":[74],"over":[75],"355,641":[76],"spanning":[78],"various":[79],"patterns,":[81],"with":[82],"primary":[84],"focus":[85],"on":[86],"English,":[87],"Mandarin,":[88],"other":[90],"languages.We":[91],"expect":[92],"Codemix":[94],"Corpus":[95],"to":[96],"serve":[97],"foundational":[100],"dataset":[101,112],"research":[103],"computational":[105],"linguistics,":[106],"sociolinguistics,":[107],"NLP":[109],"applications.Code":[110],"sample":[113],"can":[114],"be":[115],"found":[116],"here.":[117]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-13T00:00:00"}
