{"id":"https://openalex.org/W4210784023","doi":"https://doi.org/10.1145/3510419","title":"Reduplication in Assamese: Identification and Modeling","display_name":"Reduplication in Assamese: Identification and Modeling","publication_year":2022,"publication_date":"2022-02-03","ids":{"openalex":"https://openalex.org/W4210784023","doi":"https://doi.org/10.1145/3510419"},"language":"en","primary_location":{"id":"doi:10.1145/3510419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3510419","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/A5056545771","display_name":"Dhrubajyoti Pathak","orcid":"https://orcid.org/0000-0001-8094-3620"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhrubajyoti Pathak","raw_affiliation_strings":["Indian Institute of Technology Guwahati, Guwahati, India"],"raw_orcid":"https://orcid.org/0000-0001-8094-3620","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053883070","display_name":"Sukumar Nandi","orcid":"https://orcid.org/0000-0002-5869-1057"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sukumar Nandi","raw_affiliation_strings":["Indian Institute of Technology Guwahati, Guwahati, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006141263","display_name":"Priyankoo Sarmah","orcid":"https://orcid.org/0000-0002-9051-1255"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyankoo Sarmah","raw_affiliation_strings":["Indian Institute of Technology Guwahati, Guwahati, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.9185,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77625412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"5","first_page":"1","last_page":"18"},"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":0.9987999796867371,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reduplication","display_name":"Reduplication","score":0.9930843114852905},{"id":"https://openalex.org/keywords/assamese","display_name":"Assamese","score":0.9903172254562378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.59560626745224},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49091964960098267},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4868685305118561},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44438251852989197},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4353383481502533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4177861511707306},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0942787230014801},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.0657888650894165}],"concepts":[{"id":"https://openalex.org/C196368558","wikidata":"https://www.wikidata.org/wiki/Q221446","display_name":"Reduplication","level":2,"score":0.9930843114852905},{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.9903172254562378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.59560626745224},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49091964960098267},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4868685305118561},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44438251852989197},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4353383481502533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4177861511707306},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0942787230014801},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0657888650894165},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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:10.1145/3510419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3510419","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":17,"referenced_works":["https://openalex.org/W614818492","https://openalex.org/W617156065","https://openalex.org/W629174275","https://openalex.org/W803770162","https://openalex.org/W1997049674","https://openalex.org/W2030825277","https://openalex.org/W2103029213","https://openalex.org/W2106181999","https://openalex.org/W2484912135","https://openalex.org/W2512604152","https://openalex.org/W2514864449","https://openalex.org/W2782940483","https://openalex.org/W2902567446","https://openalex.org/W2956021784","https://openalex.org/W4229563017","https://openalex.org/W4302909688","https://openalex.org/W6620166425"],"related_works":["https://openalex.org/W70126818","https://openalex.org/W2595800753","https://openalex.org/W4283367889","https://openalex.org/W2482063950","https://openalex.org/W3136670730","https://openalex.org/W4213367687","https://openalex.org/W2186325032","https://openalex.org/W4210784023","https://openalex.org/W3174543885","https://openalex.org/W2394308601"],"abstract_inverted_index":{"Reduplication":[0,17],"is":[1,18,64,100,103,151],"a":[2,9,19,45,107,162],"productive":[3],"morphological":[4],"process":[5],"widely":[6],"used":[7],"in":[8,14,34,48,68,72,90,112],"substantial":[10],"number":[11],"of":[12,32,36,51,83,96,117,143,172],"languages":[13,38,74],"the":[15,37,40,49,118,128,154],"world.":[16,41],"well-studied":[20],"phenomenon,":[21],"and":[22,85,140,146],"several":[23],"typological":[24],"works":[25],"have":[26],"provided":[27],"evidence":[28],"for":[29],"different":[30,81,123],"types":[31,82],"reduplication":[33,43,84,97,111,156],"most":[35],"around":[39],"Addressing":[42],"plays":[44],"vital":[46],"role":[47],"efficiency":[50],"POS":[52],"tagger,":[53],"sentiment":[54],"analysis,":[55],"as":[56,58],"well":[57],"other":[59],"NLP":[60],"tasks.":[61],"However,":[62],"it":[63,150],"an":[65,93,136],"understudied":[66],"area":[67],"computational":[69],"linguistics,":[70],"especially":[71],"low-resource":[73],"like":[75],"Assamese.":[76,91],"This":[77],"article":[78],"first":[79],"describes":[80],"their":[86,177],"shapes":[87],"that":[88,102,127,153],"occur":[89],"Second,":[92],"exhaustive":[94],"set":[95],"formation":[98],"rules":[99],"compiled":[101],"incorporated":[104],"to":[105,109],"build":[106],"system":[108,130],"identify":[110,132],"Assamese":[113,155],"text.":[114],"The":[115],"results":[116],"experiments":[119],"performed":[120],"on":[121],"three":[122],"domain":[124],"datasets":[125],"showed":[126],"rule-based":[129],"can":[131,158],"reduplicated":[133],"expressions":[134],"with":[135,176],"average":[137],"precision,":[138],"recall,":[139],"F1":[141],"scores":[142],"94.19%,":[144],"98.07%,":[145],"96.07%,":[147],"respectively.":[148],"Third,":[149],"shown":[152],"processes":[157,174],"be":[159],"captured":[160],"through":[161],"two-way":[163],"finite-state":[164],"transducer":[165],"(2-way":[166],"FST).":[167],"Finally,":[168],"two":[169],"broad":[170],"categories":[171],"reduplicative":[173],"along":[175],"corresponding":[178],"2-way":[179],"FST":[180],"model":[181],"are":[182],"presented.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}