{"id":"https://openalex.org/W4280637746","doi":"https://doi.org/10.1145/3502157","title":"A Lemmatizer for Low-resource Languages: WSD and Its Role in the Assamese Language","display_name":"A Lemmatizer for Low-resource Languages: WSD and Its Role in the Assamese Language","publication_year":2022,"publication_date":"2022-05-17","ids":{"openalex":"https://openalex.org/W4280637746","doi":"https://doi.org/10.1145/3502157"},"language":"en","primary_location":{"id":"doi:10.1145/3502157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502157","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/A5041272563","display_name":"Arjun Gogoi","orcid":"https://orcid.org/0000-0002-0574-9868"},"institutions":[{"id":"https://openalex.org/I64128412","display_name":"Dibrugarh University","ror":"https://ror.org/045kfbt16","country_code":"IN","type":"education","lineage":["https://openalex.org/I64128412"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arjun Gogoi","raw_affiliation_strings":["Dibrugarh University, Dibrugarh, India"],"affiliations":[{"raw_affiliation_string":"Dibrugarh University, Dibrugarh, India","institution_ids":["https://openalex.org/I64128412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062431070","display_name":"Nomi Baruah","orcid":"https://orcid.org/0000-0003-4965-9933"},"institutions":[{"id":"https://openalex.org/I64128412","display_name":"Dibrugarh University","ror":"https://ror.org/045kfbt16","country_code":"IN","type":"education","lineage":["https://openalex.org/I64128412"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nomi Baruah","raw_affiliation_strings":["Dibrugarh University, Dibrugarh, India"],"affiliations":[{"raw_affiliation_string":"Dibrugarh University, Dibrugarh, India","institution_ids":["https://openalex.org/I64128412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041272563"],"corresponding_institution_ids":["https://openalex.org/I64128412"],"apc_list":null,"apc_paid":null,"fwci":1.0613,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80214553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"22"},"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":0.9988999962806702,"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":0.9958000183105469,"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/assamese","display_name":"Assamese","score":0.9984403848648071},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.9224071502685547},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.799168586730957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6617141366004944},{"id":"https://openalex.org/keywords/root","display_name":"Root (linguistics)","score":0.6586791276931763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5987118482589722},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5655970573425293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167416930198669},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.48045581579208374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3332196772098541},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06551158428192139}],"concepts":[{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.9984403848648071},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.9224071502685547},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.799168586730957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6617141366004944},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.6586791276931763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5987118482589722},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5655970573425293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167416930198669},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48045581579208374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3332196772098541},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06551158428192139},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3502157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502157","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":22,"referenced_works":["https://openalex.org/W3851596","https://openalex.org/W1525193954","https://openalex.org/W1819204739","https://openalex.org/W1971220772","https://openalex.org/W2026227174","https://openalex.org/W2031391805","https://openalex.org/W2035717317","https://openalex.org/W2078257655","https://openalex.org/W2097835057","https://openalex.org/W2104732277","https://openalex.org/W2131514140","https://openalex.org/W2248403171","https://openalex.org/W2251386579","https://openalex.org/W2285811659","https://openalex.org/W2436001372","https://openalex.org/W2544314166","https://openalex.org/W2563066736","https://openalex.org/W2901191773","https://openalex.org/W2953924753","https://openalex.org/W3033718133","https://openalex.org/W3169853576","https://openalex.org/W4235505822"],"related_works":["https://openalex.org/W4280637746","https://openalex.org/W4281690118","https://openalex.org/W1561563106","https://openalex.org/W2116831595","https://openalex.org/W2103574067","https://openalex.org/W2393370774","https://openalex.org/W2078257655","https://openalex.org/W3144673486","https://openalex.org/W2884860922","https://openalex.org/W3042025871"],"abstract_inverted_index":{"The":[0],"morphological":[1,65],"variations":[2],"of":[3,15,84,89,173,214,258],"highly":[4,70,232],"inflected":[5,71],"languages":[6,62],"that":[7,121,144,183,252],"appear":[8],"in":[9,64,80,117,156,207],"a":[10,28,33,96,119,129,197],"text":[11],"impede":[12],"the":[13,81,100,134,145,159,169,181,208,212,217,220,256,260],"progress":[14],"computer":[16],"processing":[17],"and":[18,38,153,158,180,192,200,250],"root":[19],"word":[20,131],"determination":[21],"tasks":[22],"while":[23],"extracting":[24],"an":[25,114],"abstract.":[26],"As":[27],"remedy":[29],"to":[30,132,149],"this":[31,92,229],"difficulty,":[32],"lemmatization":[34,213],"algorithm":[35],"is":[36,41,53,86,147,196,222,264],"developed,":[37],"its":[39,50],"effectiveness":[40,257],"evaluated":[42,162,224],"for":[43,55,61,225,240],"Word":[44],"Sense":[45],"Disambiguation":[46],"(WSD).":[47],"Having":[48],"observed":[49,143,251],"usefulness,":[51],"lemmatizer":[52,116,146,221],"considered":[54],"developing":[56],"Natural":[57],"Language":[58],"Processing":[59],"tools":[60],"rich":[63],"variations.":[66],"Among":[67],"various":[68,164],"Indian":[69],"languages,":[72],"Assamese,":[73,157],"spoken":[74],"by":[75],"over":[76],"14":[77],"million":[78],"people":[79],"North-Eastern":[82],"region":[83],"India,":[85],"also":[87,245],"one":[88],"them.":[90],"In":[91],"present":[93],"work,":[94],"after":[95],"detailed":[97],"study":[98],"on":[99,128,163],"possible":[101],"transformations":[102,124],"through":[103],"which":[104,263],"surface":[105,130,175],"words":[106,176,235],"are":[107,236],"created":[108],"from":[109,168],"lemmas,":[110],"we":[111],"have":[112,244],"designed":[113],"Assamese":[115,165,170,195,209,226,234],"such":[118,253],"manner":[120],"suitable":[122],"reverse":[123],"can":[125],"be":[126],"employed":[127],"derive":[133],"co-relative":[135],"(similar)":[136],"lemma":[137],"back.":[138],"And":[139],"it":[140,184],"has":[141,204],"been":[142,205],"competent":[148],"deal":[150],"with":[151,186],"inflectional":[152],"derivational":[154],"morphology":[155],"same":[160],"was":[161,189],"articles":[166],"extracted":[167],"Corpus":[171],"consisting":[172],"50,000":[174],"(excluding":[177],"proper":[178],"nouns),":[179],"result":[182,218],"yielded":[185],"82%":[187],"accuracy":[188],"quite":[190],"encouraging":[191],"satisfying,":[193],"as":[194],"low-level":[198],"language":[199,210],"no":[201],"research":[202],"work":[203],"done":[206],"regarding":[211],"words.":[215],"Considering":[216],"obtained,":[219],"then":[223],"WSD.":[227],"For":[228],"purpose,":[230],"10":[231],"polysemous":[233],"taken":[237],"into":[238],"account":[239],"sense":[241],"disambiguation.":[242],"We":[243],"regarded":[246],"varied":[247],"WSD":[248,261],"systems":[249,254],"enhance":[255],"all":[259],"systems,":[262],"statistically":[265],"significant.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}