{"id":"https://openalex.org/W2798348125","doi":"https://doi.org/10.18653/v1/p18-1143","title":"Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data","display_name":"Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798348125","doi":"https://doi.org/10.18653/v1/p18-1143","mag":"2798348125"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1143","pdf_url":"https://www.aclweb.org/anthology/P18-1143.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1143.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019864606","display_name":"Adithya Pratapa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Adithya Pratapa","raw_affiliation_strings":["Microsoft Research, Bangalore, India","{t-pradi,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"{t-pradi,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085218914","display_name":"Gayatri Bhat","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gayatri Bhat","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":["Microsoft Research, Bangalore, India","{t-pradi,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"{t-pradi,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005513786","display_name":"Sunayana Sitaram","orcid":"https://orcid.org/0000-0003-4251-9719"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunayana Sitaram","raw_affiliation_strings":["Microsoft Research, Bangalore, India","{t-pradi,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"{t-pradi,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006779728","display_name":"Sandipan Dandapat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandipan Dandapat","raw_affiliation_strings":["Microsoft R&D, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Microsoft R&D, Hyderabad, India","institution_ids":["https://openalex.org/I4210162141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013639574","display_name":"Kalika Bali","orcid":"https://orcid.org/0000-0001-9275-742X"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kalika Bali","raw_affiliation_strings":["Microsoft Research, Bangalore, India","{t-pradi,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Bangalore, India","institution_ids":["https://openalex.org/I4210124949"]},{"raw_affiliation_string":"{t-pradi,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019864606"],"corresponding_institution_ids":["https://openalex.org/I4210124949"],"apc_list":null,"apc_paid":null,"fwci":12.0541,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.98742769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1543","last_page":"1553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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":0.6677930355072021},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5755718946456909},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.5680376887321472},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5325034856796265},{"id":"https://openalex.org/keywords/code-mixing","display_name":"Code-mixing","score":0.5223099589347839},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49869441986083984},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.4870786964893341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3951171040534973},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3728331923484802},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.1659938395023346},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.15223726630210876},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11663204431533813},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07344040274620056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6677930355072021},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5755718946456909},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.5680376887321472},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5325034856796265},{"id":"https://openalex.org/C2778598016","wikidata":"https://www.wikidata.org/wiki/Q3201279","display_name":"Code-mixing","level":3,"score":0.5223099589347839},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49869441986083984},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.4870786964893341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3951171040534973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3728331923484802},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1659938395023346},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.15223726630210876},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11663204431533813},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07344040274620056},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1143","pdf_url":"https://www.aclweb.org/anthology/P18-1143.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1143","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1143","pdf_url":"https://www.aclweb.org/anthology/P18-1143.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":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798348125.pdf","grobid_xml":"https://content.openalex.org/works/W2798348125.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W44716798","https://openalex.org/W179875071","https://openalex.org/W1541518680","https://openalex.org/W1575384945","https://openalex.org/W1590009191","https://openalex.org/W1605308203","https://openalex.org/W1969754958","https://openalex.org/W1970026646","https://openalex.org/W1985258458","https://openalex.org/W2002019621","https://openalex.org/W2014962660","https://openalex.org/W2034585809","https://openalex.org/W2097606805","https://openalex.org/W2100506586","https://openalex.org/W2108015785","https://openalex.org/W2139645402","https://openalex.org/W2140679639","https://openalex.org/W2145867197","https://openalex.org/W2148708890","https://openalex.org/W2149778059","https://openalex.org/W2236357521","https://openalex.org/W2250548009","https://openalex.org/W2251149908","https://openalex.org/W2252095989","https://openalex.org/W2295078202","https://openalex.org/W2338893019","https://openalex.org/W2402268235","https://openalex.org/W2407467516","https://openalex.org/W2525997790","https://openalex.org/W2560970694","https://openalex.org/W2571593272","https://openalex.org/W2593383075","https://openalex.org/W2807157666","https://openalex.org/W2962920413","https://openalex.org/W2963293280","https://openalex.org/W2990897930","https://openalex.org/W4237155282","https://openalex.org/W4285719527","https://openalex.org/W4297813410"],"related_works":["https://openalex.org/W4390411868","https://openalex.org/W2734357165","https://openalex.org/W2794189087","https://openalex.org/W2946888518","https://openalex.org/W143242002","https://openalex.org/W2264886721","https://openalex.org/W2966074984","https://openalex.org/W4385376720","https://openalex.org/W1960112736","https://openalex.org/W2800058963"],"abstract_inverted_index":{"Adithya":[0],"Pratapa,":[1],"Gayatri":[2],"Bhat,":[3],"Monojit":[4],"Choudhury,":[5],"Sunayana":[6],"Sitaram,":[7],"Sandipan":[8],"Dandapat,":[9],"Kalika":[10],"Bali.":[11],"Proceedings":[12],"of":[13,18],"the":[14,19],"56th":[15],"Annual":[16],"Meeting":[17],"Association":[20],"for":[21],"Computational":[22],"Linguistics":[23],"(Volume":[24],"1:":[25],"Long":[26],"Papers).":[27],"2018.":[28]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}