{"id":"https://openalex.org/W4416034936","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.422","title":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","display_name":"COMI-LINGUA: Expert Annotated Large-Scale Dataset for Multitask NLP in Hindi-English Code-Mixing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034936","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.422"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.422","pdf_url":"https://aclanthology.org/2025.findings-emnlp.422.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.422.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rajvee Sheth","orcid":null},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajvee Sheth","raw_affiliation_strings":["Research Group , Indian Institute of Technology Gandhinagar , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Group , Indian Institute of Technology Gandhinagar , India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083148760","display_name":"Himanshu Beniwal","orcid":"https://orcid.org/0000-0001-6389-576X"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Himanshu Beniwal","raw_affiliation_strings":["Research Group , Indian Institute of Technology Gandhinagar , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Group , Indian Institute of Technology Gandhinagar , India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100746903","display_name":"Mayank Singh","orcid":"https://orcid.org/0000-0002-8393-3652"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayank Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95691902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7973","last_page":"7992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5117999911308289,"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":0.5117999911308289,"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":0.12229999899864197,"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":0.061500001698732376,"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/task","display_name":"Task (project management)","score":0.3057999908924103},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.2870999872684479},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2768999934196472},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.27379998564720154},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.265500009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754000186920166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406999826431274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5924000144004822},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.24320000410079956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.422","pdf_url":"https://aclanthology.org/2025.findings-emnlp.422.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.422","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.422","pdf_url":"https://aclanthology.org/2025.findings-emnlp.422.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/F4320306227","display_name":"Arthritis National Research Foundation","ror":"https://ror.org/03abbex33"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034936.pdf","grobid_xml":"https://content.openalex.org/works/W4416034936.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"COMI-LINGUA,":[2],"the":[3],"largest":[4],"manually":[5],"annotated":[6,35],"Hindi-English":[7],"code-mixed":[8,127],"dataset,":[9],"comprising":[10],"125K+":[11],"high-quality":[12],"instances":[13],"across":[14,90],"five":[15],"core":[16],"NLP":[17],"tasks:":[18],"Tokenlevel":[19],"Language":[20,23],"Identification,":[21,24],"Matrix":[22],"Named":[25],"Entity":[26],"Recognition,":[27],"Part-Of-Speech":[28],"Tagging":[29],"and":[30,54,60,63,79,98,118],"Machine":[31],"Translation.Each":[32],"instance":[33],"is":[34,129],"by":[36],"three":[37],"bilingual":[38],"annotators,":[39],"yielding":[40],"over":[41],"376K":[42],"expert":[43],"annotations":[44],"with":[45],"strong":[46],"inter-annotator":[47],"agreement":[48],"(Fleiss'":[49],"Kappa":[50],"0.81).The":[51],"rigorously":[52],"preprocessed":[53],"filtered":[55],"dataset":[56],"covers":[57],"both":[58],"Devanagari":[59],"Roman":[61],"scripts":[62],"spans":[64],"diverse":[65],"domains,":[66],"ensuring":[67],"real-world":[68],"linguistic":[69],"coverage.Evaluation":[70],"reveals":[71],"that":[72],"closedweight":[73],"LLMs":[74,101],"significantly":[75],"outperform":[76],"traditional":[77],"tools":[78],"open-weight":[80,100],"models":[81],"in":[82,93,112,116],"zeroshot":[83],"settings.Notably,":[84],"one-shot":[85],"prompting":[86],"consistently":[87],"boosts":[88],"performance":[89],"tasks,":[91],"especially":[92],"structure-sensitive":[94],"predictions":[95],"like":[96],"POS":[97],"NER.Fine-tuning":[99],"on":[102],"COMI-LINGUA":[103],"demonstrates":[104],"substantial":[105],"improvements,":[106],"achieving":[107],"up":[108],"to":[109],"95.25":[110],"F1":[111,115],"NER,":[113],"98.77":[114],"MLI,":[117],"competitive":[119],"MT":[120],"performance,":[121],"setting":[122],"new":[123],"benchmarks":[124],"for":[125],"Hinglish":[126],"text.COMI-LINGUA":[128],"publicly":[130],"available":[131],"at":[132],"this":[133],"URL":[134],"1":[135],".":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}