{"id":"https://openalex.org/W2757746673","doi":"https://doi.org/10.1145/3129416.3129453","title":"Morphological cluster induction of Bantu words using a weighted similarity measure","display_name":"Morphological cluster induction of Bantu words using a weighted similarity measure","publication_year":2017,"publication_date":"2017-09-25","ids":{"openalex":"https://openalex.org/W2757746673","doi":"https://doi.org/10.1145/3129416.3129453","mag":"2757746673"},"language":"en","primary_location":{"id":"doi:10.1145/3129416.3129453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3129416.3129453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute of Computer Scientists and Information Technologists","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/A5087304429","display_name":"Catherine Chavula","orcid":"https://orcid.org/0000-0002-6113-1691"},"institutions":[{"id":"https://openalex.org/I157614274","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79","country_code":"ZA","type":"education","lineage":["https://openalex.org/I157614274"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Catherine Chavula","raw_affiliation_strings":["University of Cape Town, Cape Town, South Africa"],"affiliations":[{"raw_affiliation_string":"University of Cape Town, Cape Town, South Africa","institution_ids":["https://openalex.org/I157614274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009415079","display_name":"Hussein Suleman","orcid":"https://orcid.org/0000-0002-4196-1444"},"institutions":[{"id":"https://openalex.org/I157614274","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79","country_code":"ZA","type":"education","lineage":["https://openalex.org/I157614274"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Hussein Suleman","raw_affiliation_strings":["University of Cape Town, Cape Town, South Africa"],"affiliations":[{"raw_affiliation_string":"University of Cape Town, Cape Town, South Africa","institution_ids":["https://openalex.org/I157614274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087304429"],"corresponding_institution_ids":["https://openalex.org/I157614274"],"apc_list":null,"apc_paid":null,"fwci":1.5602,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87491727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12090","display_name":"Language and cultural evolution","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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/bantu-languages","display_name":"Bantu languages","score":0.8378508687019348},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7121805548667908},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.707416296005249},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6533294916152954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6499464511871338},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5268750786781311},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5249119997024536},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5229949951171875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.516000509262085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47950345277786255},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4704873859882355},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4487595856189728},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4398422837257385},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4209689497947693},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25486940145492554},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.12822186946868896}],"concepts":[{"id":"https://openalex.org/C99878080","wikidata":"https://www.wikidata.org/wiki/Q33146","display_name":"Bantu languages","level":2,"score":0.8378508687019348},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7121805548667908},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.707416296005249},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6533294916152954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6499464511871338},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5268750786781311},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5249119997024536},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5229949951171875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.516000509262085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47950345277786255},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4704873859882355},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4487595856189728},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4398422837257385},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4209689497947693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25486940145492554},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.12822186946868896},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations 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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3129416.3129453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3129416.3129453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the South African Institute of Computer Scientists and Information Technologists","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W3174715","https://openalex.org/W18265741","https://openalex.org/W72960384","https://openalex.org/W432983366","https://openalex.org/W646755065","https://openalex.org/W1518518886","https://openalex.org/W1583936759","https://openalex.org/W1870418615","https://openalex.org/W1968951234","https://openalex.org/W1985057352","https://openalex.org/W1992419399","https://openalex.org/W2016004628","https://openalex.org/W2053306448","https://openalex.org/W2055063781","https://openalex.org/W2060907774","https://openalex.org/W2087991154","https://openalex.org/W2098181012","https://openalex.org/W2126377586","https://openalex.org/W2138958299","https://openalex.org/W2141684702","https://openalex.org/W2163963178","https://openalex.org/W2169147927","https://openalex.org/W2250447695","https://openalex.org/W2523561069","https://openalex.org/W2581848328","https://openalex.org/W2951408652","https://openalex.org/W4388351880"],"related_works":["https://openalex.org/W2538341397","https://openalex.org/W2501899044","https://openalex.org/W2013556410","https://openalex.org/W1875057406","https://openalex.org/W2250538341","https://openalex.org/W2806955548","https://openalex.org/W2403232536","https://openalex.org/W4385342823","https://openalex.org/W4214807560","https://openalex.org/W2757746673"],"abstract_inverted_index":{"Unsupervised":[0],"morphological":[1,41,135],"segmentation":[2,120],"is":[3,82],"attractive":[4],"for":[5,36,54,86],"low":[6],"density":[7],"languages":[8,37,99],"that":[9,23,32,38,50,68,105],"have":[10,39],"little":[11],"linguistic":[12],"description,":[13],"such":[14],"as":[15],"many":[16],"of":[17,74,95],"the":[18,96,106,116,126,133],"Bantu":[19,98],"languages.":[20,79],"However,":[21],"techniques":[22],"cluster":[24],"morphologically":[25],"related":[26],"words":[27],"use":[28],"string":[29],"similarity":[30,48,110],"metrics":[31],"are":[33,69,130],"more":[34],"suited":[35],"simple":[40],"systems.":[42],"This":[43],"paper":[44],"proposes":[45],"a":[46],"weighted":[47,108],"measure":[49],"uses":[51],"normal":[52],"distribution":[53],"calculating":[55],"Ordered":[56],"Weighted":[57],"Aggregator":[58],"(OWA)":[59],"operator":[60],"weights.":[61],"The":[62,80],"weighting":[63],"favours":[64],"shared":[65],"character":[66],"sequences":[67],"likely":[70],"to":[71,92,132],"be":[72],"part":[73],"stems":[75],"in":[76],"highly":[77],"agglutinative":[78],"approach":[81],"evaluated":[83],"on":[84,122],"text":[85],"Chichewa":[87],"and":[88],"Citumbuka,":[89],"both":[90],"belonging":[91],"group":[93],"N":[94],"Guthrie":[97],"classification.":[100],"Cluster":[101],"analysis":[102,136],"results":[103,121],"show":[104],"proposed":[107],"word":[109],"metric":[111,129],"produces":[112],"better":[113],"clusters":[114,123],"than":[115],"Dice":[117],"Coefficient.":[118],"Morpheme":[119],"generated":[124],"using":[125],"OWA":[127],"weights":[128],"comparable":[131],"state-of-the-art":[134],"tools.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
