{"id":"https://openalex.org/W2962722852","doi":"https://doi.org/10.18653/v1/d17-1240","title":"All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media","display_name":"All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media","publication_year":2017,"publication_date":"2017-07-25","ids":{"openalex":"https://openalex.org/W2962722852","doi":"https://doi.org/10.18653/v1/d17-1240","mag":"2962722852"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1707.08446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.08446","pdf_url":"https://arxiv.org/pdf/1707.08446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.08446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025398442","display_name":"Jasabanta Patro","orcid":"https://orcid.org/0000-0003-2461-9679"},"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":"Patro, Jasabanta","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058145190","display_name":"Bidisha Samanta","orcid":"https://orcid.org/0000-0002-0000-2650"},"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":"Samanta, Bidisha","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012194189","display_name":"Saurabh Singh","orcid":"https://orcid.org/0000-0002-0797-6538"},"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":"Singh, Saurabh","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024530563","display_name":"Abhipsa Basu","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":false,"raw_author_name":"Basu, Abhipsa","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012594038","display_name":"Prithwish Mukherjee","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":false,"raw_author_name":"Mukherjee, Prithwish","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","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/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Choudhury, Monojit","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, India -721302"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, India -721302","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020991141","display_name":"Animesh Mukherjee","orcid":"https://orcid.org/0000-0003-4534-0044"},"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":"Mukherjee, Animesh","raw_affiliation_strings":["Microsoft Research India, Bangalore -560001"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India, Bangalore -560001","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"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/computer-science","display_name":"Computer science","score":0.8058537244796753},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7468580007553101},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6979721188545227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6784465909004211},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6091259717941284},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5934684872627258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5898141860961914},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5770066380500793},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.553488552570343},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5184190273284912},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4621790945529938},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34421005845069885},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22546491026878357},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09471592307090759},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07965001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058537244796753},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7468580007553101},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6979721188545227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6784465909004211},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6091259717941284},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5934684872627258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898141860961914},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5770066380500793},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.553488552570343},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5184190273284912},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4621790945529938},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34421005845069885},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22546491026878357},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09471592307090759},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07965001463890076},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:1707.08446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.08446","pdf_url":"https://arxiv.org/pdf/1707.08446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.08446","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.08446","pdf_url":"https://arxiv.org/pdf/1707.08446","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W79217024","https://openalex.org/W594384242","https://openalex.org/W1537058117","https://openalex.org/W1537230416","https://openalex.org/W1607008085","https://openalex.org/W1974288322","https://openalex.org/W1975879668","https://openalex.org/W2039827492","https://openalex.org/W2080404274","https://openalex.org/W2107198622","https://openalex.org/W2107251449","https://openalex.org/W2107550813","https://openalex.org/W2135064956","https://openalex.org/W2139645402","https://openalex.org/W2145867197","https://openalex.org/W2161490380","https://openalex.org/W2176715178","https://openalex.org/W2183465848","https://openalex.org/W2250548009","https://openalex.org/W2251149908","https://openalex.org/W2251402695","https://openalex.org/W2251678408","https://openalex.org/W2279505618","https://openalex.org/W2306738223","https://openalex.org/W2307020448","https://openalex.org/W2395626303","https://openalex.org/W2462558730","https://openalex.org/W2560970694","https://openalex.org/W2739818192","https://openalex.org/W2740885753","https://openalex.org/W2741636242","https://openalex.org/W4232332215","https://openalex.org/W4237155282","https://openalex.org/W4241834849","https://openalex.org/W4285719527","https://openalex.org/W4387627603"],"related_works":["https://openalex.org/W226586525","https://openalex.org/W4239051087","https://openalex.org/W2362145681","https://openalex.org/W2913520953","https://openalex.org/W1538826769","https://openalex.org/W4310801723","https://openalex.org/W2383292628","https://openalex.org/W1543103045","https://openalex.org/W2067569787","https://openalex.org/W2079798264"],"abstract_inverted_index":{"In":[0,26,79],"this":[1,61],"paper,":[2],"we":[3,64],"present":[4],"a":[5,15,101],"set":[6],"of":[7,14,28,72,82,106],"computational":[8],"methods":[9,34],"to":[10,49,67],"identify":[11],"the":[12,21,45,50,69,84,88],"likeliness":[13,47,62],"word":[16],"being":[17],"borrowed,":[18],"based":[19],"on":[20,60],"signals":[22],"from":[23],"social":[24],"media.":[25],"terms":[27],"Spearman":[29],"correlation":[30],"coefficient":[31],"values,":[32],"our":[33],"perform":[35],"more":[36],"than":[37],"two":[38],"times":[39],"better":[40],"(nearly":[41,54],"0.62)":[42],"in":[43,57,75],"predicting":[44],"borrowing":[46],"compared":[48],"best":[51],"performing":[52],"baseline":[53],"0.26)":[55],"reported":[56],"literature.":[58],"Based":[59],"estimate":[63],"asked":[65],"annotators":[66,85],"re-annotate":[68],"language":[70,90,97,108],"tags":[71],"foreign":[73,89],"words":[74],"predominantly":[76],"native":[77,96],"contexts.":[78],"88":[80],"percent":[81],"cases":[83],"felt":[86],"that":[87],"tag":[91],"should":[92],"be":[93],"replaced":[94],"by":[95],"tag,":[98],"thus":[99],"indicating":[100],"huge":[102],"scope":[103],"for":[104],"improvement":[105],"automatic":[107],"identification":[109],"systems.":[110]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2019-07-30T00:00:00"}