{"id":"https://openalex.org/W1970072068","doi":"https://doi.org/10.4304/jsw.9.7.1818-1826","title":"Challenges of Diacritical Marker or Hudhaa Character in Tokenization of Oromo Text","display_name":"Challenges of Diacritical Marker or Hudhaa Character in Tokenization of Oromo Text","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W1970072068","doi":"https://doi.org/10.4304/jsw.9.7.1818-1826","mag":"1970072068"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.7.1818-1826","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.7.1818-1826","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5079342172","display_name":"Abraham Tesso Nedjo","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Abraham Tesso Nedjo","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Degen Huang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100705973","display_name":"Xiaoxia Liu","orcid":"https://orcid.org/0000-0002-2289-7520"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxia Liu","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.4142,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72808418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":"7","first_page":null,"last_page":null},"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":0.9991999864578247,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9876000285148621,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9077218174934387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8252550363540649},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7716237306594849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5631635189056396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4718197286128998},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3482402563095093}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9077218174934387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252550363540649},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7716237306594849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5631635189056396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4718197286128998},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3482402563095093},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.4304/jsw.9.7.1818-1826","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.7.1818-1826","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"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":8,"referenced_works":["https://openalex.org/W142212369","https://openalex.org/W1532325895","https://openalex.org/W1579838312","https://openalex.org/W1999127688","https://openalex.org/W2105180486","https://openalex.org/W2117364574","https://openalex.org/W2140717391","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W3192589309","https://openalex.org/W2601638452","https://openalex.org/W4300598845","https://openalex.org/W2285263069","https://openalex.org/W4376107815","https://openalex.org/W4319309603","https://openalex.org/W4319309671","https://openalex.org/W1599985958","https://openalex.org/W1748623649"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,38,61,84,120,130,137],"tokenization":[3,39],"in":[4,17,73,107],"natural":[5],"language":[6,34],"processing":[7],"is":[8,65,103],"to":[9,13,68,99],"find":[10],"a":[11,18,66,104],"way":[12],"get":[14],"every":[15],"token":[16],"text.":[19],"For":[20],"languages":[21],"like":[22,97],"Oromo,":[23],"for":[24,88],"which,":[25],"much":[26],"effort":[27],"has":[28],"not":[29],"been":[30],"done":[31],"yet":[32],"regarding":[33],"processing,":[35],"the":[36,59,82,118],"task":[37],"by":[40,57,141],"no":[41],"means":[42],"cannot":[43],"be":[44],"overlooked.":[45],"This":[46],"paper":[47],"reports":[48],"on":[49,123],"Oromo":[50,74,131],"tokenizer":[51],"that":[52],"we":[53,79,116],"designed":[54],"and":[55,134],"tested":[56],"accommodating":[58],"challenge":[60],"diacritical":[62,89],"marker-Hudhaa":[63],"which":[64],"sign":[67],"represent":[69],"in-word":[70],"glottal":[71],"sound":[72],"language.":[75],"In":[76],"this":[77,142],"work,":[78],"have":[80],"studied":[81],"effect":[83],"using":[85,93],"acute":[86],"accent":[87],"mark":[90],"rather":[91],"than":[92],"other":[94],"confusing":[95],"marks":[96],"right-quote":[98],"write":[100],"Hudhaa.":[101],"Accuracy":[102],"prime":[105],"factor":[106],"evaluating":[108],"any":[109],"Natural":[110],"Language":[111],"Processing":[112],"(NLP)":[113],"system.":[114],"So":[115],"measured":[117],"accuracy":[119,136],"our":[121],"system":[122],"1.2MB":[124],"(9686":[125],"sentences":[126],"having":[127],"164932":[128],"words)":[129],"text":[132],"data":[133],"an":[135],"99.94%":[138],"was":[139],"achieved":[140],"algorithm.":[143]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
