{"id":"https://openalex.org/W4393140115","doi":"https://doi.org/10.1109/tcss.2024.3360378","title":"A Comprehensive Understanding of Code-Mixed Language Semantics Using Hierarchical Transformer","display_name":"A Comprehensive Understanding of Code-Mixed Language Semantics Using Hierarchical Transformer","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4393140115","doi":"https://doi.org/10.1109/tcss.2024.3360378"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2024.3360378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3360378","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006685910","display_name":"Tharun Suresh","orcid":"https://orcid.org/0000-0001-5280-9328"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tharun Suresh","raw_affiliation_strings":["Department of Computer Science and Engineering, IIIT-Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0001-5280-9328","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIIT-Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973342","display_name":"Ayan Sengupta","orcid":"https://orcid.org/0000-0001-6298-3207"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ayan Sengupta","raw_affiliation_strings":["Department of Electrical Engineering, IIT Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0001-6298-3207","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066369545","display_name":"Md Shad Akhtar","orcid":"https://orcid.org/0000-0002-2033-2382"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Md Shad Akhtar","raw_affiliation_strings":["Department of Computer Science and Engineering, IIIT-Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-2033-2382","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, IIIT-Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046521217","display_name":"Tanmoy Chakraborty","orcid":"https://orcid.org/0000-0002-0210-0369"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanmoy Chakraborty","raw_affiliation_strings":["Department of Electrical Engineering, IIT Delhi, Delhi, India"],"raw_orcid":"https://orcid.org/0000-0002-0210-0369","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, IIT Delhi, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006685910"],"corresponding_institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":3.9736,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94151513,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"11","issue":"3","first_page":"4139","last_page":"4148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8989999890327454,"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":0.8989999890327454,"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/T12031","display_name":"Speech and dialogue systems","score":0.8569999933242798,"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":0.7537999749183655,"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/computer-science","display_name":"Computer science","score":0.6224969625473022},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5764390230178833},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.44278284907341003},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43928125500679016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3570130467414856},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15913942456245422},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.076192706823349}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6224969625473022},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5764390230178833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.44278284907341003},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43928125500679016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3570130467414856},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15913942456245422},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.076192706823349},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2024.3360378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2024.3360378","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2142074148","https://openalex.org/W2154652894","https://openalex.org/W2236357521","https://openalex.org/W2250854016","https://openalex.org/W2251058040","https://openalex.org/W2251765408","https://openalex.org/W2470673105","https://openalex.org/W2606974598","https://openalex.org/W2769280657","https://openalex.org/W2798348125","https://openalex.org/W2803633004","https://openalex.org/W2886146035","https://openalex.org/W2886890203","https://openalex.org/W2887800417","https://openalex.org/W2891252302","https://openalex.org/W2896457183","https://openalex.org/W2898762441","https://openalex.org/W2962795068","https://openalex.org/W2964308564","https://openalex.org/W2976852125","https://openalex.org/W3034559121","https://openalex.org/W3035280234","https://openalex.org/W3035390927","https://openalex.org/W3098670961","https://openalex.org/W3098911752","https://openalex.org/W3104723404","https://openalex.org/W3115081393","https://openalex.org/W3136221257","https://openalex.org/W3165484287","https://openalex.org/W3169483174","https://openalex.org/W3171471761","https://openalex.org/W3175810781","https://openalex.org/W3177057799","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6682631176","https://openalex.org/W6752610543","https://openalex.org/W6755207826","https://openalex.org/W6765643788","https://openalex.org/W6773843597","https://openalex.org/W6777795097","https://openalex.org/W6778883912","https://openalex.org/W6780226713","https://openalex.org/W6791709101"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Being":[0],"a":[1,32,72],"popular":[2],"mode":[3],"of":[4,28,39,43,81,86,103,153,182],"text-based":[5],"communication":[6],"in":[7,12,63],"multilingual":[8,139],"communities,":[9],"code":[10],"mixing":[11],"online":[13],"social":[14],"media":[15],"has":[16],"become":[17],"an":[18],"important":[19],"subject":[20],"to":[21,36,77,95],"study.":[22],"Learning":[23],"the":[24,37,41,79,98,108,151,154,175,180],"semantics":[25,80],"and":[26,45,59,90,100,120,122,138,166],"morphology":[27],"code-mixed":[29,82,104,135],"language":[30,53,140,159],"remains":[31],"key":[33],"challenge":[34],"due":[35],"scarcity":[38],"data,":[40],"unavailability":[42],"robust,":[44],"language-invariant":[46],"representation":[47,136],"learning":[48,64,137,164,168],"techniques.":[49],"Any":[50],"morphologically":[51],"rich":[52],"can":[54],"benefit":[55],"from":[56],"character,":[57],"subword,":[58],"word-level":[60],"embeddings,":[61],"aiding":[62],"meaningful":[65],"correlations.":[66],"In":[67],"this":[68],"article,":[69],"we":[70],"explore":[71],"hierarchical":[73],"transformer":[74],"(HIT)-based":[75],"architecture":[76,156],"learn":[78],"languages.":[83],"HIT":[84,131,155],"consists":[85],"multiheaded":[87],"self-attention":[88],"(MSA)":[89],"outer":[91],"product":[92],"attention":[93],"components":[94],"simultaneously":[96],"comprehend":[97],"semantic":[99],"syntactic":[101],"structures":[102],"texts.":[105],"We":[106,148],"evaluate":[107],"proposed":[109],"method":[110],"across":[111,145],"six":[112],"Indian":[113],"languages":[114],"(Bengali,":[115],"Gujarati,":[116],"Hindi,":[117],"Tamil,":[118],"Telugu,":[119],"Malayalam)":[121],"Spanish":[123],"for":[124],"nine":[125],"tasks":[126],"on":[127,142],"17":[128],"datasets.":[129],"The":[130],"model":[132],"outperforms":[133],"state-of-the-art":[134],"models":[141],"13":[143],"datasets":[144],"eight":[146],"tasks.":[147,184],"further":[149],"demonstrate":[150],"generalizability":[152],"using":[157],"masked":[158],"modeling":[160],"(MLM)-based":[161],"pretraining,":[162],"zero-shot":[163],"(ZSL),":[165],"transfer":[167],"approaches.":[169],"Our":[170],"empirical":[171],"results":[172],"show":[173],"that":[174],"pretraining":[176],"objectives":[177],"significantly":[178],"improve":[179],"performance":[181],"downstream":[183]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}