{"id":"https://openalex.org/W4281721917","doi":"https://doi.org/10.1145/3531478","title":"IsiXhosa Named Entity Recognition Resources","display_name":"IsiXhosa Named Entity Recognition Resources","publication_year":2022,"publication_date":"2022-06-02","ids":{"openalex":"https://openalex.org/W4281721917","doi":"https://doi.org/10.1145/3531478"},"language":"en","primary_location":{"id":"doi:10.1145/3531478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531478","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/A5027603954","display_name":"Roald Eiselen","orcid":"https://orcid.org/0000-0002-8612-5175"},"institutions":[{"id":"https://openalex.org/I27765905","display_name":"North-West University","ror":"https://ror.org/010f1sq29","country_code":"ZA","type":"education","lineage":["https://openalex.org/I27765905"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Roald Eiselen","raw_affiliation_strings":["Centre for Text Technology, North-West University, Potchefstroom, South Africa"],"raw_orcid":"https://orcid.org/0000-0002-8612-5175","affiliations":[{"raw_affiliation_string":"Centre for Text Technology, North-West University, Potchefstroom, South Africa","institution_ids":["https://openalex.org/I27765905"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004241641","display_name":"Andiswa Bukula","orcid":"https://orcid.org/0000-0002-6667-4599"},"institutions":[{"id":"https://openalex.org/I27765905","display_name":"North-West University","ror":"https://ror.org/010f1sq29","country_code":"ZA","type":"education","lineage":["https://openalex.org/I27765905"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Andiswa Bukula","raw_affiliation_strings":["South African Centre for Digital Language Resources, North-West University, Potchefstroom, South Africa"],"raw_orcid":"https://orcid.org/0000-0002-6667-4599","affiliations":[{"raw_affiliation_string":"South African Centre for Digital Language Resources, North-West University, Potchefstroom, South Africa","institution_ids":["https://openalex.org/I27765905"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52925763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9794999957084656,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.8632502555847168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7989099621772766},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7390303015708923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7044993042945862},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6992862820625305},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.6741594076156616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5764604806900024},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.573230504989624},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5344478487968445},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5114516019821167},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.42023175954818726},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3037438988685608},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.10139721632003784}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8632502555847168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989099621772766},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7390303015708923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7044993042945862},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6992862820625305},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.6741594076156616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5764604806900024},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.573230504989624},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5344478487968445},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5114516019821167},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.42023175954818726},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3037438988685608},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.10139721632003784},{"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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1145/3531478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3531478","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":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W438054","https://openalex.org/W80901941","https://openalex.org/W149084605","https://openalex.org/W1580467103","https://openalex.org/W1985057352","https://openalex.org/W2000363133","https://openalex.org/W2004763266","https://openalex.org/W2020278455","https://openalex.org/W2033599040","https://openalex.org/W2056354103","https://openalex.org/W2096765155","https://openalex.org/W2135958840","https://openalex.org/W2138780451","https://openalex.org/W2141099517","https://openalex.org/W2143345705","https://openalex.org/W2144578941","https://openalex.org/W2158897288","https://openalex.org/W2295405141","https://openalex.org/W2296283641","https://openalex.org/W2339643030","https://openalex.org/W2593713917","https://openalex.org/W2803301173","https://openalex.org/W2888794009","https://openalex.org/W2915429162","https://openalex.org/W2933138175","https://openalex.org/W2946119234","https://openalex.org/W2962739339","https://openalex.org/W2963186636","https://openalex.org/W2970119519","https://openalex.org/W2970463839","https://openalex.org/W2971039193","https://openalex.org/W3000409384","https://openalex.org/W3104415840","https://openalex.org/W4237530236","https://openalex.org/W4240560945","https://openalex.org/W4243743514"],"related_works":["https://openalex.org/W4250494529","https://openalex.org/W2399696375","https://openalex.org/W2614126974","https://openalex.org/W11196620","https://openalex.org/W1964783010","https://openalex.org/W2759598007","https://openalex.org/W2790570950","https://openalex.org/W2590599429","https://openalex.org/W4281721917","https://openalex.org/W2251120091"],"abstract_inverted_index":{"Named":[0],"entity":[1,44,51,59,81,135,180],"recognition":[2],"has":[3,32,149],"been":[4,33],"one":[5],"of":[6,40,49,63,78,101,122,143,169],"the":[7,16,21,38,41,64,79,86,92,97,109,123,133,144,178],"most":[8],"widely":[9],"researched":[10],"natural":[11],"language":[12],"processing":[13],"technologies":[14],"over":[15],"past":[17],"two":[18],"decades.":[19],"For":[20],"South":[22],"African":[23],"languages,":[24],"however,":[25],"relatively":[26,155],"little":[27],"research":[28],"and":[29,54,75,106,114,137],"development":[30],"work":[31],"done.":[34],"This":[35],"changed":[36],"with":[37],"release":[39,186],"NCHLT":[42,145],"named":[43,50,58,80,134,179],"annotated":[45,52,83],"resources,":[46],"a":[47,72,184,188],"collection":[48],"data":[53,84],"Conditional":[55],"Random":[56],"Field-based":[57],"recognisers":[60],"for":[61,85,160,187],"ten":[62],"official":[65],"languages.":[66],"In":[67],"this":[68,182],"work,":[69],"we":[70,111,131],"provide":[71],"detailed":[73],"description":[74],"linguistic":[76],"analysis":[77],"(NE)":[82],"agglutinative":[87],"isiXhosa":[88],"language,":[89],"by":[90],"analysing":[91],"morphosyntactic":[93],"features":[94,116],"relevant":[95],"to":[96,176],"three":[98],"main":[99],"types":[100],"NE,":[102],"viz.":[103],"person,":[104],"location,":[105],"organisation.":[107],"From":[108],"data,":[110],"identify":[112],"suffix":[113],"capitalisation":[115],"that":[117],"may":[118],"be":[119],"good":[120],"predictors":[121],"different":[124],"NE":[125],"types.":[126],"Based":[127],"on":[128],"these":[129],"features,":[130],"describe":[132],"recogniser":[136,148],"feature":[138],"set":[139],"developed":[140],"as":[141],"part":[142],"release.":[146],"The":[147],"high":[150],"precision,":[151],"0.9713":[152],"overall,":[153],"but":[154],"low":[156],"recall,":[157],"0.7409,":[158],"especially":[159],"person":[161],"names,":[162],"0.5963,":[163],"resulting":[164],"in":[165],"an":[166],"overall":[167],"F-score":[168],"0.8406.":[170],"Although":[171],"there":[172],"are":[173],"various":[174],"avenues":[175],"improve":[177],"recogniser,":[181],"is":[183],"significant":[185],"historically":[189],"under-resourced":[190],"language.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}