{"id":"https://openalex.org/W2891252302","doi":"https://doi.org/10.18653/v1/d18-1344","title":"Word Embeddings for Code-Mixed Language Processing","display_name":"Word Embeddings for Code-Mixed Language Processing","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891252302","doi":"https://doi.org/10.18653/v1/d18-1344","mag":"2891252302"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1344","pdf_url":"https://www.aclweb.org/anthology/D18-1344.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1344.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, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"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, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","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, India"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, India","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019864606"],"corresponding_institution_ids":["https://openalex.org/I4210124949"],"apc_list":null,"apc_paid":null,"fwci":6.2441,"has_fulltext":true,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97125266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3067","last_page":"3072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9991999864578247,"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":0.9923999905586243,"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":0.8417211174964905},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.8334694504737854},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7386854290962219},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.692327618598938},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6909188032150269},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6700989007949829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5930314660072327},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.5580844879150391},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43769463896751404},{"id":"https://openalex.org/keywords/code-mixing","display_name":"Code-mixing","score":0.4318670630455017},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.365337073802948},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26444387435913086},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15832030773162842},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1255892515182495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417211174964905},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.8334694504737854},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7386854290962219},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.692327618598938},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6909188032150269},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6700989007949829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5930314660072327},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.5580844879150391},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43769463896751404},{"id":"https://openalex.org/C2778598016","wikidata":"https://www.wikidata.org/wiki/Q3201279","display_name":"Code-mixing","level":3,"score":0.4318670630455017},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.365337073802948},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26444387435913086},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15832030773162842},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1255892515182495},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1344","pdf_url":"https://www.aclweb.org/anthology/D18-1344.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1344","pdf_url":"https://www.aclweb.org/anthology/D18-1344.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891252302.pdf","grobid_xml":"https://content.openalex.org/works/W2891252302.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W342285082","https://openalex.org/W1590009191","https://openalex.org/W1828724394","https://openalex.org/W1969754958","https://openalex.org/W2002019621","https://openalex.org/W2014962660","https://openalex.org/W2047259421","https://openalex.org/W2068297964","https://openalex.org/W2108015785","https://openalex.org/W2118090838","https://openalex.org/W2139645402","https://openalex.org/W2142074148","https://openalex.org/W2145867197","https://openalex.org/W2149778059","https://openalex.org/W2153579005","https://openalex.org/W2229725139","https://openalex.org/W2236357521","https://openalex.org/W2251149908","https://openalex.org/W2251678408","https://openalex.org/W2251765408","https://openalex.org/W2338893019","https://openalex.org/W2478432301","https://openalex.org/W2560970694","https://openalex.org/W2561042415","https://openalex.org/W2567058318","https://openalex.org/W2574536432","https://openalex.org/W2626534681","https://openalex.org/W2740885753","https://openalex.org/W2741986357","https://openalex.org/W2798348125","https://openalex.org/W2952037945","https://openalex.org/W2962702662","https://openalex.org/W2962795068","https://openalex.org/W2962920413","https://openalex.org/W2963293280","https://openalex.org/W3098911752","https://openalex.org/W4237155282","https://openalex.org/W4294170691","https://openalex.org/W4297813410"],"related_works":["https://openalex.org/W4205878333","https://openalex.org/W2755033583","https://openalex.org/W2508660901","https://openalex.org/W1485736417","https://openalex.org/W4378378905","https://openalex.org/W3166060075","https://openalex.org/W4389308877","https://openalex.org/W153744606","https://openalex.org/W3181795562","https://openalex.org/W2938595889"],"abstract_inverted_index":{"We":[0],"compare":[1],"three":[2],"existing":[3,76],"bilingual":[4,77],"word":[5,95],"embedding":[6,52,78,96],"approaches,":[7],"and":[8,30,42,56,87],"a":[9,90],"novel":[10],"approach":[11,62],"of":[12,23],"training":[13],"skip-grams":[14],"on":[15,25,54],"synthetic":[16],"code-mixed":[17,34,84,99],"text":[18,85],"generated":[19],"through":[20],"linguistic":[21],"models":[22],"code-mixing,":[24],"two":[26],"tasks":[27,58,69],"-sentiment":[28],"analysis":[29],"POS":[31],"tagging":[32],"for":[33,67,83,92],"text.":[35,100],"Our":[36],"results":[37],"show":[38],"that":[39,75],"while":[40],"CVM":[41],"CCA":[43],"based":[44],"embeddings":[45],"perform":[46],"as":[47,49],"well":[48],"the":[50,60,64,98],"proposed":[51,61],"technique":[53],"semantic":[55],"syntactic":[57],"respectively,":[59],"provides":[63],"best":[65],"performance":[66],"both":[68],"overall.":[70],"Thus,":[71],"this":[72],"study":[73],"demonstrates":[74],"techniques":[79],"are":[80],"not":[81],"ideal":[82],"processing":[86],"there":[88],"is":[89],"need":[91],"learning":[93],"multilingual":[94],"from":[97]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}