{"id":"https://openalex.org/W4412393281","doi":"https://doi.org/10.1145/3748312","title":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","display_name":"From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412393281","doi":"https://doi.org/10.1145/3748312"},"language":"en","primary_location":{"id":"doi:10.1145/3748312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748312","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3748312","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083888032","display_name":"Prashant Kodali","orcid":"https://orcid.org/0000-0002-7542-6802"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prashant Kodali","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0000-0002-7542-6802","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051727084","display_name":"Anmol Goel","orcid":"https://orcid.org/0009-0009-4807-2402"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["DE","IN"],"is_corresponding":false,"raw_author_name":"Anmol Goel","raw_affiliation_strings":["IIIT Hyderabad","TU Darmstadt","IIIT Hyderabad, Gachibowli, India and TU Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0009-4807-2402","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"TU Darmstadt","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India and TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782","https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097424548","display_name":"Likhith Asapu","orcid":"https://orcid.org/0009-0007-3366-0231"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Likhith Asapu","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0009-0007-3366-0231","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036184764","display_name":"Vamshi Bonagiri","orcid":"https://orcid.org/0000-0002-5537-1664"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vamshi Krishna Bonagiri","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0000-0002-5537-1664","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112174656","display_name":"Anirudh Govil","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anirudh Govil","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0009-0009-3479-6258","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008944385","display_name":"Monojit Choudhury","orcid":"https://orcid.org/0000-0001-7473-7839"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":["MBZUAI","MBZUAI, Masdar City, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-7473-7839","affiliations":[{"raw_affiliation_string":"MBZUAI","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"MBZUAI, Masdar City, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077509916","display_name":"Ponnurangam Kumaraguru","orcid":"https://orcid.org/0000-0001-5082-2078"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ponnurangam Kumaraguru","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0000-0001-5082-2078","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013675579","display_name":"Manish Shrivastava","orcid":"https://orcid.org/0000-0001-8705-6637"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manish Shrivastava","raw_affiliation_strings":["IIIT Hyderabad","IIIT Hyderabad, Gachibowli, India"],"raw_orcid":"https://orcid.org/0000-0001-8705-6637","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT Hyderabad, Gachibowli, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2216,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84316846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"9","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.998199999332428,"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":0.9632999897003174,"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/code","display_name":"Code (set theory)","score":0.548244833946228},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4617595374584198},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42393726110458374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4202845096588135},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17910516262054443}],"concepts":[{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.548244833946228},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4617595374584198},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42393726110458374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4202845096588135},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17910516262054443},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3748312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748312","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3748312","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748312","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748312","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412393281.pdf","grobid_xml":"https://content.openalex.org/works/W4412393281.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W336825802","https://openalex.org/W1501668372","https://openalex.org/W2014962660","https://openalex.org/W2061272101","https://openalex.org/W2066267250","https://openalex.org/W2078735333","https://openalex.org/W2108015785","https://openalex.org/W2168708086","https://openalex.org/W2530571334","https://openalex.org/W2531882892","https://openalex.org/W2725872906","https://openalex.org/W2747481658","https://openalex.org/W2952638691","https://openalex.org/W2963285772","https://openalex.org/W2978670439","https://openalex.org/W2979826702","https://openalex.org/W2996728628","https://openalex.org/W3001434439","https://openalex.org/W3024308166","https://openalex.org/W3034284720","https://openalex.org/W3034775979","https://openalex.org/W3035390927","https://openalex.org/W3045153201","https://openalex.org/W3099919888","https://openalex.org/W3153869297","https://openalex.org/W3155192455","https://openalex.org/W3156404059","https://openalex.org/W3169483174","https://openalex.org/W3171877493","https://openalex.org/W3173954987","https://openalex.org/W4200444669","https://openalex.org/W4205859589","https://openalex.org/W4221152690","https://openalex.org/W4229892888","https://openalex.org/W4241834849","https://openalex.org/W4285243619","https://openalex.org/W4385573158","https://openalex.org/W4389519066","https://openalex.org/W4389523734","https://openalex.org/W4412272069"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Current":[0],"computational":[1],"approaches":[2],"for":[3,34,65,233,280],"analysing":[4],"or":[5,14],"generating":[6],"code-mixed":[7,17,29,38,45,52,68,89,118,236,259],"sentences":[8],"do":[9],"not":[10,185],"explicitly":[11],"model":[12,248,284],"\u201cnaturalness\u201d":[13],"\u201cacceptability\u201d":[15],"of":[16,27,37,51,74,81,109,130,220,266],"sentences,":[18,79],"but":[19],"rely":[20],"on":[21,226],"training":[22],"corpora":[23,119],"to":[24,116,187,242,252,257],"reflect":[25],"distribution":[26],"acceptable":[28],"sentences.":[30],"Modelling":[31],"human":[32,62,124],"judgement":[33],"the":[35,72,128,194],"acceptability":[36,63,125,244],"text":[39,46,90],"can":[40],"help":[41],"in":[42,235],"distinguishing":[43],"natural":[44],"and":[47,91,166,217,262,278,283],"enable":[48],"quality-controlled":[49],"generation":[50,282],"text.":[53,69],"To":[54],"this":[55],"end,":[56],"we":[57],"construct":[58],"Cline\u2014a":[59],"dataset":[60],"containing":[61],"judgements":[64],"English-Hindi":[66],"(en-hi)":[67],"Cline":[70,135],"is":[71],"largest":[73],"its":[75],"kind":[76],"with":[77,123,198,202,215],"16,642":[78],"consisting":[80],"samples":[82,92],"sourced":[83],"from":[84,94,240],"two":[85],"sources:":[86],"synthetically":[87],"generated":[88],"collected":[93],"online":[95],"social":[96],"media.":[97],"Our":[98],"analysis":[99],"establishes":[100],"that":[101,137,223],"popular":[102],"code-mixing":[103,147],"metrics":[104,148],"such":[105],"as":[106,149],"CMI,":[107],"Number":[108],"Switch":[110],"Points,":[111],"Burstines,":[112],"which":[113],"are":[114,151,184],"used":[115],"filter/curate/compare":[117],"have":[120],"low":[121],"correlation":[122],"judgements,":[126],"underlining":[127],"necessity":[129],"our":[131,247,271],"dataset.":[132],"Experiments":[133],"using":[134,146,246],"demonstrate":[136],"simple":[138],"Multilayer":[139],"Perceptron":[140],"(MLP)":[141],"models":[142,164,183,192,207],"when":[143,196],"trained":[144,274],"solely":[145],"features":[150],"outperformed":[152],"by":[153],"fine-tuned":[154,225],"pre-trained":[155],"Multilingual":[156],"Large":[157],"Language":[158],"Models":[159],"(MLLMs).":[160],"Specifically,":[161],"among":[162],"Encoder":[163],"XLM-Roberta":[165],"Bernice":[167],"outperform":[168,188,229],"IndicBERT":[169],"across":[170],"different":[171],"configurations.":[172],"Among":[173],"Encoder-Decoder":[174,182],"models,":[175],"mBART":[176],"performs":[177],"better":[178],"than":[179],"mT5,":[180],"however,":[181],"able":[186],"Encoder-only":[189],"models.":[190,213],"Decoder-only":[191],"perform":[193],"best":[195],"compared":[197],"all":[199],"other":[200,258],"MLLMS,":[201],"Llama":[203],"3.2":[204],"-":[205],"3B":[206],"outperforming":[208],"similarly":[209],"sized":[210],"Qwen,":[211],"Phi":[212],"Comparison":[214],"zero":[216],"fewshot":[218],"capabilitites":[219],"ChatGPT":[221],"show":[222],"MLLMs":[224],"larger":[227],"data":[228,281],"ChatGPT,":[230],"providing":[231,263],"scope":[232],"improvement":[234],"tasks.":[237],"Zero-shot":[238],"transfer":[239],"English\u2013Hindi":[241],"English-Telugu":[243],"judgments":[245],"checkpoints":[249],"proves":[250],"superior":[251],"random":[253],"baselines,":[254],"enabling":[255],"application":[256],"language":[260],"pairs":[261],"further":[264],"avenues":[265],"research.":[267],"We":[268],"publicly":[269],"release":[270],"human-annotated":[272],"dataset,":[273],"checkpoints,":[275],"code-mix":[276],"corpus,":[277],"code":[279],"training.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}