{"id":"https://openalex.org/W4386378676","doi":"https://doi.org/10.1145/3617653","title":"Part-of-speech Tagger for Assamese Using Ensembling Approach","display_name":"Part-of-speech Tagger for Assamese Using Ensembling Approach","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386378676","doi":"https://doi.org/10.1145/3617653"},"language":"en","primary_location":{"id":"doi:10.1145/3617653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617653","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":true,"raw_author_name":"Dhrubajyoti Pathak","raw_affiliation_strings":["Indian Institute of Technology Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology 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, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology 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, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056545771"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.8728,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78840888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"22","issue":"10","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9577341079711914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8348737359046936},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.6606053113937378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6555783152580261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6373339295387268},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4785062372684479},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.47558343410491943},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4323994815349579},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.4212127923965454},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.42047086358070374},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12199652194976807}],"concepts":[{"id":"https://openalex.org/C2777834912","wikidata":"https://www.wikidata.org/wiki/Q29401","display_name":"Assamese","level":2,"score":0.9577341079711914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348737359046936},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.6606053113937378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6555783152580261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6373339295387268},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4785062372684479},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.47558343410491943},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4323994815349579},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.4212127923965454},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.42047086358070374},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12199652194976807},{"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:10.1145/3617653","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3617653","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":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W426598361","https://openalex.org/W803770162","https://openalex.org/W1483301097","https://openalex.org/W1524281572","https://openalex.org/W1614298861","https://openalex.org/W1631063262","https://openalex.org/W1940872118","https://openalex.org/W1988066969","https://openalex.org/W2044025798","https://openalex.org/W2110448499","https://openalex.org/W2130942839","https://openalex.org/W2144839729","https://openalex.org/W2250539671","https://openalex.org/W2296283641","https://openalex.org/W2325944896","https://openalex.org/W2493916176","https://openalex.org/W2554327043","https://openalex.org/W2560674852","https://openalex.org/W2603456266","https://openalex.org/W2759245808","https://openalex.org/W2798569372","https://openalex.org/W2884001105","https://openalex.org/W2905221922","https://openalex.org/W2953356739","https://openalex.org/W2962717763","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W3035390927","https://openalex.org/W3099919888","https://openalex.org/W3100276395","https://openalex.org/W4205918858","https://openalex.org/W4210784023","https://openalex.org/W4213069590","https://openalex.org/W4235929402","https://openalex.org/W4317600295","https://openalex.org/W6640362995","https://openalex.org/W6679436768","https://openalex.org/W6762554868"],"related_works":["https://openalex.org/W4280637746","https://openalex.org/W4281690118","https://openalex.org/W2044025798","https://openalex.org/W2293592765","https://openalex.org/W4386378676","https://openalex.org/W2886260596","https://openalex.org/W1965453504","https://openalex.org/W4206668191","https://openalex.org/W2902135563","https://openalex.org/W4313289405"],"abstract_inverted_index":{"Ensemble":[0,33],"system":[1,34],"for":[2,8,69,287],"part-of-speech":[3],"(POS)":[4],"tagging":[5,95,120,148,151],"is":[6,35],"beneficial":[7],"many":[9],"resource-poor":[10,111,292],"languages":[11],"that":[12,160,262],"do":[13],"not":[14,165],"have":[15],"enough":[16],"annotated":[17,191],"training":[18],"data":[19],"to":[20,39,100,167,175,178,188],"train":[21],"Deep":[22,27],"Learning":[23],"(DL,":[24],"also":[25,280],"named":[26],"Neural":[28],"Network)-based":[29],"POS":[30,55,108,119,147,197,233,255],"taggers.":[31,56],"An":[32],"a":[36,45,71,110,118,128,200,231],"better":[37],"choice":[38],"incorporate":[40],"the":[41,49,87,124,142,144,161,176,180,184,208,220,226,258,265,268,274],"linguistic":[42,181],"features":[43,182],"of":[44,51,54,64,77,89,130,154,183,207,215,239,247,251,264,270],"language":[46,76,112,185,209],"and":[47,156,210,229],"leverage":[48],"benefits":[50],"various":[52],"types":[53],"In":[57],"this":[58,278],"work,":[59],"we":[60,194,218,241],"present":[61],"our":[62,252],"experiment":[63],"developing":[65,104],"an":[66,212,236,243],"ensemble":[67,237,254,282],"tagger":[68,198,234],"Assamese,":[70],"low-resource,":[72],"morphologically":[73,290],"rich":[74,291],"scheduled":[75],"India,":[78],"spoken":[79],"by":[80],"more":[81,285],"than":[82],"15":[83],"million":[84],"people.":[85],"Despite":[86],"success":[88],"modern":[90],"neural-network-based":[91],"models":[92,149],"in":[93,103,109,273],"sequence":[94],"tasks,":[96],"it":[97],"has":[98],"yet":[99],"receive":[101],"attention":[102],"tasks":[105],"such":[106,113],"as":[107,114],"Assamese.":[115],"We":[116,133,158],"develop":[117,230],"model":[121],"based":[122],"on":[123],"BiLSTM-CRF":[125],"architecture":[126],"with":[127,225],"corpus":[129],"404k":[131],"tokens.":[132],"cover":[134],"several":[135,204],"word":[136],"embeddings":[137],"during":[138],"training.":[139],"Among":[140],"all":[141,271],"experiments,":[143],"top":[145,221],"two":[146,222],"achieve":[150,168],"F1":[152,213,245],"scores":[153],"0.746":[155],"0.745.":[157],"observe":[159],"DL-based":[162,223],"taggers":[163,224,256,260,266,272,283],"are":[164,284],"able":[166],"decent":[169],"accuracy.":[170],"It":[171],"may":[172],"be":[173],"due":[174,187],"inability":[177],"capture":[179],"or":[186],"comparatively":[189],"less":[190],"data.":[192],"So,":[193],"build":[195],"another":[196],"using":[199,235],"rule-based":[201,227],"approach":[202],"considering":[203],"morphological":[205],"phenomena":[206],"get":[211,242],"score":[214,246],"0.85.":[216],"Subsequently,":[217],"integrate":[219],"ones":[228],"new":[232,253,275],"approach,":[238],"which":[240],"improved":[244],"0.925.":[248],"Performance":[249],"improvement":[250],"over":[257],"baseline":[259],"suggests":[261],"integration":[263],"combines":[267],"qualities":[269],"tagger.":[276],"Therefore,":[277],"study":[279],"states":[281],"suitable":[286],"highly":[288],"inflectional,":[289],"languages.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}