{"id":"https://openalex.org/W4229030698","doi":"https://doi.org/10.1145/3477314.3507066","title":"Named-entity recognition for a low-resource language using pre-trained language model","display_name":"Named-entity recognition for a low-resource language using pre-trained language model","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229030698","doi":"https://doi.org/10.1145/3477314.3507066"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507066","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-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/A5032014024","display_name":"Hailemariam Mehari Yohannes","orcid":"https://orcid.org/0000-0003-0617-0900"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hailemariam Mehari Yohannes","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025604052","display_name":"Toshiyuki Amagasa","orcid":"https://orcid.org/0000-0003-0595-2230"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiyuki Amagasa","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032014024"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":2.8325,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92304431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T13629","display_name":"Text Readability and Simplification","score":0.9907000064849854,"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/computer-science","display_name":"Computer science","score":0.8695302605628967},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.8053563833236694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7298239469528198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7153418660163879},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6274292469024658},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5704357624053955},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5570971369743347},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.47800934314727783},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.45525962114334106},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4137089252471924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33436527848243713},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23120474815368652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8695302605628967},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8053563833236694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7298239469528198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7153418660163879},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6274292469024658},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5704357624053955},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5570971369743347},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.47800934314727783},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.45525962114334106},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4137089252471924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33436527848243713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23120474815368652},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507066","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507066","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2000363133","https://openalex.org/W2107878631","https://openalex.org/W2250539671","https://openalex.org/W2473679434","https://openalex.org/W2493916176","https://openalex.org/W2531638282","https://openalex.org/W2789889349","https://openalex.org/W2942768244","https://openalex.org/W2963625095","https://openalex.org/W3014595877","https://openalex.org/W3125631070","https://openalex.org/W3140747828","https://openalex.org/W3207937903","https://openalex.org/W4323285614"],"related_works":["https://openalex.org/W11196620","https://openalex.org/W2614126974","https://openalex.org/W1964783010","https://openalex.org/W2759598007","https://openalex.org/W4399144739","https://openalex.org/W2277628282","https://openalex.org/W2590599429","https://openalex.org/W3201257042","https://openalex.org/W2251120091","https://openalex.org/W3180764077"],"abstract_inverted_index":{"This":[0,35],"paper":[1],"proposes":[2],"a":[3,10,15,21,85,125],"method":[4,144,165],"for":[5,9,59,90,124,148,153],"Named-Entity":[6],"Recognition":[7],"(NER)":[8],"low-resource":[11],"language,":[12,24],"Tigrinya,":[13],"using":[14,110],"pre-trained":[16,87],"language":[17,88],"model.":[18,170],"Tigrinya":[19,91,108],"is":[20,36,103,157],"morphologically":[22],"rich":[23],"although":[25],"one":[26],"of":[27,33,43,120,127,134],"the":[28,31,40,53,72,118,143,163,168],"underrepresented":[29],"in":[30],"field":[32],"NLP.":[34],"mainly":[37],"due":[38],"to":[39,98,162],"limited":[41],"amount":[42],"annotated":[44,69],"data":[45],"available.":[46],"To":[47],"address":[48],"this":[49],"problem,":[50],"we":[51,83,96,116],"introduced":[52],"first":[54],"publicly":[55],"available":[56],"NER":[57,131,149],"dataset":[58,62],"Tigrinya.":[60],"The":[61,138],"contains":[63],"69,309":[64],"tokens":[65],"that":[66,142],"were":[67],"manually":[68],"based":[70,92,166],"on":[71,93,105,167],"CoNLL":[73],"2003":[74],"Beginning,":[75],"Inside,":[76],"and":[77,132,150],"Outside":[78],"(BIO)":[79],"tagging":[80],"schema.":[81],"Specifically,":[82],"develop":[84],"new":[86],"model":[89],"RoBERTa,":[94],"which":[95,156],"refer":[97],"as":[99],"TigRoBERTa.":[100],"First,":[101],"It":[102],"trained":[104],"an":[106],"unsupervised":[107],"corpus":[109],"Masked":[111],"Language":[112],"Modeling":[113],"(MLM).":[114],"Then,":[115],"show":[117,141],"validity":[119],"TigRoBERTa":[121],"by":[122],"fine-tuning":[123],"couple":[126],"downstream":[128],"tasks,":[129],"namely,":[130],"Part":[133],"Speech":[135],"(POS)":[136],"tagging.":[137],"experimental":[139],"results":[140],"achieved":[145],"81.05%":[146],"F1-score":[147],"92%":[151],"accuracy":[152],"POS":[154],"tagging,":[155],"better":[158],"than":[159],"or":[160],"comparable":[161],"baseline":[164],"CNN-BiLSTM-CRF":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}