{"id":"https://openalex.org/W4225112709","doi":"https://doi.org/10.1145/3531535","title":"Am I a Resource-Poor Language? Data Sets, Embeddings, Models and Analysis for four different NLP Tasks in Telugu Language","display_name":"Am I a Resource-Poor Language? Data Sets, Embeddings, Models and Analysis for four different NLP Tasks in Telugu Language","publication_year":2022,"publication_date":"2022-04-29","ids":{"openalex":"https://openalex.org/W4225112709","doi":"https://doi.org/10.1145/3531535"},"language":"en","primary_location":{"id":"doi:10.1145/3531535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531535","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","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/A5062052248","display_name":"Mounika Marreddy","orcid":"https://orcid.org/0000-0003-1184-640X"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mounika Marreddy","raw_affiliation_strings":["IIITH, Hyderabad, Telengana, India"],"raw_orcid":"https://orcid.org/0000-0003-1184-640X","affiliations":[{"raw_affiliation_string":"IIITH, Hyderabad, Telengana, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029606497","display_name":"Subba Reddy Oota","orcid":"https://orcid.org/0000-0002-5975-622X"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subba Reddy Oota","raw_affiliation_strings":["IIITH, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0002-5975-622X","affiliations":[{"raw_affiliation_string":"IIITH, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089168458","display_name":"Lakshmi Sireesha Vakada","orcid":"https://orcid.org/0000-0002-8398-576X"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Lakshmi Sireesha Vakada","raw_affiliation_strings":["IIITH, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0002-8398-576X","affiliations":[{"raw_affiliation_string":"IIITH, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090790415","display_name":"Venkata Charan Chinni","orcid":"https://orcid.org/0000-0003-4573-1096"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Venkata Charan Chinni","raw_affiliation_strings":["IIITH, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0003-4573-1096","affiliations":[{"raw_affiliation_string":"IIITH, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038314215","display_name":"Radhika Mamidi","orcid":"https://orcid.org/0000-0003-0171-0816"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Radhika Mamidi","raw_affiliation_strings":["IIITH, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0003-0171-0816","affiliations":[{"raw_affiliation_string":"IIITH, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0521,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92314904,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9995999932289124,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9995999932289124,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9991000294685364,"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":0.9973999857902527,"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/telugu","display_name":"Telugu","score":0.9940062761306763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.803101122379303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433070540428162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7405510544776917},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4932360053062439},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48887747526168823},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4241217374801636},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4220593273639679},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24915063381195068}],"concepts":[{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.9940062761306763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.803101122379303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433070540428162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7405510544776917},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4932360053062439},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48887747526168823},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4241217374801636},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4220593273639679},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24915063381195068},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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:10.1145/3531535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531535","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W1566289585","https://openalex.org/W1589554437","https://openalex.org/W1726481707","https://openalex.org/W1832693441","https://openalex.org/W1871142974","https://openalex.org/W1924770834","https://openalex.org/W1966797434","https://openalex.org/W2021108748","https://openalex.org/W2022204871","https://openalex.org/W2026130194","https://openalex.org/W2040467972","https://openalex.org/W2064675550","https://openalex.org/W2072322795","https://openalex.org/W2091084672","https://openalex.org/W2104210067","https://openalex.org/W2108712612","https://openalex.org/W2112422413","https://openalex.org/W2115758952","https://openalex.org/W2116702209","https://openalex.org/W2118852500","https://openalex.org/W2120615054","https://openalex.org/W2138388410","https://openalex.org/W2139517011","https://openalex.org/W2148143831","https://openalex.org/W2160660844","https://openalex.org/W2163455955","https://openalex.org/W2170240176","https://openalex.org/W2181854537","https://openalex.org/W2250539671","https://openalex.org/W2250901552","https://openalex.org/W2250966211","https://openalex.org/W2251379416","https://openalex.org/W2252381721","https://openalex.org/W2311430799","https://openalex.org/W2340954483","https://openalex.org/W2469055036","https://openalex.org/W2473419285","https://openalex.org/W2473555522","https://openalex.org/W2493916176","https://openalex.org/W2514776376","https://openalex.org/W2529281176","https://openalex.org/W2537838974","https://openalex.org/W2552027021","https://openalex.org/W2556888587","https://openalex.org/W2559655401","https://openalex.org/W2565649476","https://openalex.org/W2569656908","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2740302294","https://openalex.org/W2741447225","https://openalex.org/W2758321674","https://openalex.org/W2760392765","https://openalex.org/W2787560479","https://openalex.org/W2790325757","https://openalex.org/W2796080846","https://openalex.org/W2796452002","https://openalex.org/W2806872289","https://openalex.org/W2810907558","https://openalex.org/W2887428522","https://openalex.org/W2893200234","https://openalex.org/W2912018209","https://openalex.org/W2914120296","https://openalex.org/W2962949606","https://openalex.org/W2964199361","https://openalex.org/W2964236337","https://openalex.org/W2965373594","https://openalex.org/W2970166416","https://openalex.org/W2975059944","https://openalex.org/W2978017171","https://openalex.org/W2996428491","https://openalex.org/W3038047279","https://openalex.org/W3100779964","https://openalex.org/W3106003309","https://openalex.org/W3202379861","https://openalex.org/W4212774754","https://openalex.org/W4288097928","https://openalex.org/W4289489216","https://openalex.org/W4298014777","https://openalex.org/W4298857826","https://openalex.org/W4300613830","https://openalex.org/W4300813905","https://openalex.org/W4302617179","https://openalex.org/W4391156274","https://openalex.org/W6691424587","https://openalex.org/W6719819555","https://openalex.org/W6759455113"],"related_works":["https://openalex.org/W2158722251","https://openalex.org/W1978971213","https://openalex.org/W1567338489","https://openalex.org/W159132833","https://openalex.org/W38394648","https://openalex.org/W2104752822","https://openalex.org/W1517743118","https://openalex.org/W2380694329","https://openalex.org/W2398825887","https://openalex.org/W3107474891"],"abstract_inverted_index":{"Due":[0],"to":[1,14,62,66,82,94],"the":[2,16,60,68,84,137,140,198,206,222,235,252,295,300],"lack":[3],"of":[4,18,70,139,174,200,237],"a":[5,71,95,101,169],"large":[6,36,102,170],"annotated":[7,103],"corpus,":[8,306],"many":[9],"resource-poor":[10,96],"Indian":[11,40],"languages":[12,41],"struggle":[13],"reap":[15],"benefits":[17],"recent":[19,63],"deep":[20],"feature":[21],"representations":[22,65,195],"in":[23,107],"Natural":[24],"Language":[25],"Processing":[26],"(NLP)":[27],".":[28,233],"Moreover,":[29],"adopting":[30],"existing":[31,223],"language":[32,97,152,287],"models":[33,153,239,288,318],"trained":[34],"on":[35,168,247,267],"English":[37],"corpora":[38],"for":[39,87,110,130,135,154,209,299,319],"is":[42,81],"often":[43],"limited":[44],"by":[45],"data":[46,104],"availability,":[47],"rich":[48],"morphological":[49],"variation,":[50],"syntax,":[51],"and":[52,122,133,145,148,166,182,204,231,261,278,281,291,312],"semantic":[53],"differences.":[54],"In":[55,76],"this":[56],"paper,":[57],"we":[58,90,126,191],"explore":[59],"traditional":[61],"efficient":[64],"overcome":[67],"challenges":[69],"low":[72],"resource":[73],"language,":[74],"Telugu.":[75,88,99,210],"particular,":[77],"our":[78,214,284,305],"main":[79],"objective":[80],"mitigate":[83],"low-resource":[85],"problem":[86],"Overall,":[89],"present":[91,205],"several":[92],"contributions":[93],"viz.":[98],"(i)":[100],"(35,142":[105],"sentences":[106,176,178,184],"each":[108],"task)":[109],"multiple":[111],"NLP":[112,202,249],"tasks":[113,203,250],"such":[114,156],"as":[115,157],"sentiment":[116,301],"analysis,":[117],"emotion":[118],"identification,":[119],"hate-speech":[120,134],"detection,":[121,124],"sarcasm":[123],"(ii)":[125],"create":[127],"different":[128,150,187,308],"lexicons":[129],"sentiment,":[131],"emotion,":[132],"improving":[136],"efficiency":[138],"models,":[141],"(iii)":[142],"pretrained":[143,151,215,225,238,286,316],"word":[144],"sentence":[146],"embeddings,":[147,311],"(iv)":[149],"Telugu":[155,171,180,188,270,285,320],"ELMo-Te":[158],",":[159,161,163,165,228,230],"BERT-Te":[160,290],"RoBERTa-Te":[162,292],"ALBERT-Te":[164],"DistilBERT-Te":[167],"corpus":[172],"consisting":[173],"8,015,588":[175],"(1,637,408":[177],"from":[179,186],"Wikipedia":[181],"6,378,180":[183],"crawled":[185],"websites).":[189],"Further,":[190],"show":[192,240],"that":[193,213,283],"these":[194],"significantly":[196],"improve":[197],"performance":[199,242],"four":[201,248,307],"benchmark":[207],"results":[208,246],"We":[211,264,303],"argue":[212],"embeddings":[216],"are":[217,321],"competitive":[218],"or":[219],"better":[220],"than":[221,243],"multilingual":[224],"models:":[226],"mBERT":[227],"XLM-R":[229],"IndicBERT":[232],"Lastly,":[234],"fine-tuning":[236],"higher":[241],"linear":[244],"probing":[245],"with":[251],"following":[253],"F1-scores:":[254],"Sentiment":[255,279],"(68.72),":[256],"Emotion":[257],"(58.04),":[258],"Hate-Speech":[259],"(64.27),":[260],"Sarcasm":[262],"(77.93).":[263],"also":[265],"experiment":[266],"publicly":[268],"available":[269,322],"datasets":[271],"(Named":[272],"Entity":[273],"Recognition,":[274],"Article":[275],"Genre":[276],"Classification,":[277],"Analysis)":[280],"find":[282],"(":[289],")":[293],"outperform":[294],"state-of-the-art":[296],"system":[297],"except":[298],"task.":[302],"open-source":[304],"datasets,":[309],"lexicons,":[310],"code":[313],"https://github.com/Cha14ran/DREAM-T.":[314],"The":[315],"Transformer":[317],"at":[323],"https://huggingface.co/ltrctelugu.":[324]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}