{"id":"https://openalex.org/W2139645402","doi":"https://doi.org/10.3115/v1/d14-1105","title":"POS Tagging of English-Hindi Code-Mixed Social Media Content","display_name":"POS Tagging of English-Hindi Code-Mixed Social Media Content","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2139645402","doi":"https://doi.org/10.3115/v1/d14-1105","mag":"2139645402"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1105","pdf_url":"https://doi.org/10.3115/v1/d14-1105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/d14-1105","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008851653","display_name":"Yogarshi Vyas","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yogarshi Vyas","raw_affiliation_strings":["University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041111343","display_name":"Spandana Gella","orcid":"https://orcid.org/0000-0003-2725-4476"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spandana Gella","raw_affiliation_strings":["Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077804592","display_name":"Jatin Sharma","orcid":"https://orcid.org/0000-0003-4105-8500"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jatin Sharma","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013639574","display_name":"Kalika Bali","orcid":"https://orcid.org/0000-0001-9275-742X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kalika Bali","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008944385","display_name":"Monojit Choudhury","orcid":"https://orcid.org/0000-0001-7473-7839"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008851653"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":16.5364,"has_fulltext":false,"cited_by_count":203,"citation_normalized_percentile":{"value":0.99454598,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"974","last_page":"979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13155","display_name":"Digital Communication and Language","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9944999814033508,"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/T10265","display_name":"Multilingual Education and Policy","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.9296960830688477},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.838883638381958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279063701629639},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.726118803024292},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.714194118976593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6451849341392517},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.627259373664856},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5773096680641174},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.5524100065231323},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5216427445411682},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.45046067237854004},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27314287424087524},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2462710738182068},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.17444872856140137}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.9296960830688477},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.838883638381958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279063701629639},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.726118803024292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.714194118976593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6451849341392517},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.627259373664856},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5773096680641174},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.5524100065231323},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5216427445411682},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.45046067237854004},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27314287424087524},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2462710738182068},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.17444872856140137},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/d14-1105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1105","pdf_url":"https://doi.org/10.3115/v1/d14-1105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.2318","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.2318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014105.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.85","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.85","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D14/D14-1105.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1105","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1105","pdf_url":"https://doi.org/10.3115/v1/d14-1105","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139645402.pdf","grobid_xml":"https://content.openalex.org/works/W2139645402.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W80999043","https://openalex.org/W127576493","https://openalex.org/W131502402","https://openalex.org/W133685279","https://openalex.org/W149482658","https://openalex.org/W371426616","https://openalex.org/W1632114991","https://openalex.org/W1974288322","https://openalex.org/W1996430422","https://openalex.org/W2013489815","https://openalex.org/W2051629332","https://openalex.org/W2068130800","https://openalex.org/W2101200183","https://openalex.org/W2102411528","https://openalex.org/W2123660869","https://openalex.org/W2132609289","https://openalex.org/W2143995218","https://openalex.org/W2145867197","https://openalex.org/W2150155583","https://openalex.org/W2157765050","https://openalex.org/W2251678408","https://openalex.org/W2251969930","https://openalex.org/W2306738223","https://openalex.org/W3018725618"],"related_works":["https://openalex.org/W2096393573","https://openalex.org/W190438618","https://openalex.org/W4385625167","https://openalex.org/W4288286832","https://openalex.org/W2954982483","https://openalex.org/W2886440583","https://openalex.org/W4229679882","https://openalex.org/W2887660679","https://openalex.org/W6244059","https://openalex.org/W2127361019"],"abstract_inverted_index":{"Code-mixing":[0],"is":[1,21],"frequently":[2],"observed":[3],"in":[4],"user":[5],"generated":[6],"content":[7,20],"on":[8],"social":[9],"media,":[10],"especially":[11],"from":[12,50],"multilingual":[13],"users.":[14],"The":[15],"linguistic":[16],"complexity":[17],"of":[18,25,45,62],"such":[19],"compounded":[22],"by":[23],"presence":[24],"spelling":[26],"vari-ations,":[27],"transliteration":[28,72],"and":[29,53,59,71],"non-adherance":[30],"to":[31,39],"formal":[32],"grammar.":[33],"We":[34],"describe":[35],"our":[36],"initial":[37],"efforts":[38],"create":[40],"a":[41],"multi-level":[42],"an-notated":[43],"corpus":[44],"Hindi-English":[46],"code-mixed":[47],"text":[48],"collated":[49],"Facebook":[51],"fo-rums,":[52],"explore":[54],"language":[55,69],"identifica-tion,":[56],"back-transliteration,":[57],"normalization":[58],"POS":[60,81],"tagging":[61,82],"this":[63],"data.":[64],"Our":[65],"re-sults":[66],"show":[67],"that":[68,79],"identification":[70],"for":[73],"Hindi":[74],"are":[75],"two":[76],"major":[77],"challenges":[78],"impact":[80],"accu-racy.":[83],"1":[84]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":37},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}