{"id":"https://openalex.org/W1971266104","doi":"https://doi.org/10.1109/isda.2014.7066258","title":"Tokenizer for the Malay language using pattern matching","display_name":"Tokenizer for the Malay language using pattern matching","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W1971266104","doi":"https://doi.org/10.1109/isda.2014.7066258","mag":"1971266104"},"language":"en","primary_location":{"id":"doi:10.1109/isda.2014.7066258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2014.7066258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 14th International Conference on Intelligent Systems Design and Applications","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/A5023692207","display_name":"Juhaida Abu Bakar","orcid":"https://orcid.org/0000-0002-0172-6677"},"institutions":[{"id":"https://openalex.org/I94625822","display_name":"Northern University of Malaysia","ror":"https://ror.org/01ss10648","country_code":"MY","type":"education","lineage":["https://openalex.org/I94625822"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Juhaida Abu Bakar","raw_affiliation_strings":["School of Computing, Universiti Utara Malaysia, 06010 Sintok, Kedah, Malaysia"],"affiliations":[{"raw_affiliation_string":"School of Computing, Universiti Utara Malaysia, 06010 Sintok, Kedah, Malaysia","institution_ids":["https://openalex.org/I94625822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070390862","display_name":"Khairuddin Omar","orcid":"https://orcid.org/0000-0003-1794-019X"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Khairuddin Omar","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000097176","display_name":"Mohammad Faidzul Nasrudin","orcid":"https://orcid.org/0000-0002-2003-8853"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohammad Faidzul Nasrudin","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011628934","display_name":"Mohd Zamri Murah","orcid":"https://orcid.org/0000-0002-3075-4781"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohd Zamri Murah","raw_affiliation_strings":["Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia"],"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence Technology, Universiti Kebangsaan Malaysia, 43600 Bangi, Selangor, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023692207"],"corresponding_institution_ids":["https://openalex.org/I94625822"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.05364209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9950000047683716,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9573000073432922,"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/computer-science","display_name":"Computer science","score":0.8863769769668579},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7959959506988525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.712835967540741},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.639028012752533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6043535470962524},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5898599028587341},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5592296123504639},{"id":"https://openalex.org/keywords/malay","display_name":"Malay","score":0.554405689239502},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.47672954201698303},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.47300559282302856},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17134344577789307},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16622933745384216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863769769668579},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7959959506988525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.712835967540741},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.639028012752533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6043535470962524},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5898599028587341},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5592296123504639},{"id":"https://openalex.org/C2776938241","wikidata":"https://www.wikidata.org/wiki/Q9237","display_name":"Malay","level":2,"score":0.554405689239502},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.47672954201698303},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.47300559282302856},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17134344577789307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16622933745384216},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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:10.1109/isda.2014.7066258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2014.7066258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 14th International Conference on Intelligent Systems Design and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3079964180","https://openalex.org/W2328052390","https://openalex.org/W375642441","https://openalex.org/W2288251828","https://openalex.org/W4253184376","https://openalex.org/W3044024082","https://openalex.org/W2487295014","https://openalex.org/W4298195702","https://openalex.org/W3093768914","https://openalex.org/W2945402993"],"abstract_inverted_index":{"Tokenization":[0],"is":[1,15,50],"a":[2,38],"fundamental":[3],"task":[4],"focused":[5],"on":[6,86],"text":[7],"processing.":[8],"Among":[9],"other":[10],"tasks,":[11],"the":[12,31,70,74,77,82,90],"segmentation":[13],"process":[14],"used":[16,94],"to":[17,40,51,68],"identify":[18],"information":[19],"units,":[20],"such":[21],"as":[22,37],"sentences":[23],"and":[24,72],"words.":[25],"In":[26],"this":[27,48],"paper,":[28],"we":[29],"discuss":[30],"Natural":[32,54],"Language":[33,55],"ToolKit":[34],"(NLTK)":[35],"tokenizer":[36],"step":[39],"manipulate":[41],"patterns":[42],"within":[43],"text.":[44],"The":[45],"purpose":[46],"of":[47,64,76],"work":[49],"build":[52],"up":[53],"Processing":[56],"(NLP)":[57],"base":[58],"for":[59,95],"Jawi":[60,78],"corpus.":[61],"A":[62],"series":[63],"experiments":[65],"was":[66],"performed,":[67],"validate":[69],"corpus":[71],"fulfill":[73],"requirement":[75],"script":[79],"tokenizer,":[80],"with":[81],"promising":[83,88],"results.":[84],"Based":[85],"these":[87],"results,":[89],"token":[91],"will":[92],"be":[93],"tagging":[96],"process.":[97]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
