{"id":"https://openalex.org/W2946425001","doi":"https://doi.org/10.1109/rivf.2019.8713693","title":"HMMs for Unsupervised Vietnamese Word Segmentation","display_name":"HMMs for Unsupervised Vietnamese Word Segmentation","publication_year":2019,"publication_date":"2019-03-01","ids":{"openalex":"https://openalex.org/W2946425001","doi":"https://doi.org/10.1109/rivf.2019.8713693","mag":"2946425001"},"language":"en","primary_location":{"id":"doi:10.1109/rivf.2019.8713693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5064947464","display_name":"Ba-Long Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Ba-Long Bui","raw_affiliation_strings":["Hanoi Uni. of Science & Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi Uni. of Science & Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102248830","display_name":"Thi-Trang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thi-Trang Nguyen","raw_affiliation_strings":["Hanoi Uni. of Science & Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi Uni. of Science & Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043447112","display_name":"Huu-Hoang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huu-Hoang Nguyen","raw_affiliation_strings":["Hanoi Uni. of Science & Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi Uni. of Science & Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070110789","display_name":"Kiem-Hieu Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Kiem-Hieu Nguyen","raw_affiliation_strings":["Hanoi Uni. of Science & Technology, Hanoi, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanoi Uni. of Science & Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.1446,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56319613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"81","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8250149488449097},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.7557128667831421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7272263765335083},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6965516805648804},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6590816378593445},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6489409804344177},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6281102895736694},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6222163438796997},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5634593367576599},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5540081858634949},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5475271344184875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.532123863697052},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4894605875015259},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.4559522271156311},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40089619159698486},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.13314220309257507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07547450065612793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0727180540561676}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250149488449097},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7557128667831421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7272263765335083},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6965516805648804},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6590816378593445},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6489409804344177},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6281102895736694},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6222163438796997},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5634593367576599},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5540081858634949},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5475271344184875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.532123863697052},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4894605875015259},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.4559522271156311},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40089619159698486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.13314220309257507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07547450065612793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0727180540561676},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/rivf.2019.8713693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2019.8713693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W27634986","https://openalex.org/W1558333962","https://openalex.org/W1586737702","https://openalex.org/W1977877104","https://openalex.org/W2036516910","https://openalex.org/W2074925295","https://openalex.org/W2097388131","https://openalex.org/W2125045406","https://openalex.org/W2140991203","https://openalex.org/W2160097208","https://openalex.org/W2165142900","https://openalex.org/W2250739653","https://openalex.org/W2251811146","https://openalex.org/W2293362876","https://openalex.org/W2563544594","https://openalex.org/W2759827652","https://openalex.org/W2896649846","https://openalex.org/W2952054097","https://openalex.org/W2963628345","https://openalex.org/W4298857067","https://openalex.org/W6601114500","https://openalex.org/W6674364790","https://openalex.org/W6683437210","https://openalex.org/W6691783218","https://openalex.org/W6744477106","https://openalex.org/W6744958764"],"related_works":["https://openalex.org/W2589064161","https://openalex.org/W2946128423","https://openalex.org/W2918555272","https://openalex.org/W2626114114","https://openalex.org/W2070240571","https://openalex.org/W2379663637","https://openalex.org/W3112070292","https://openalex.org/W155626099","https://openalex.org/W4282560693","https://openalex.org/W2559372221"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,17,32],"is":[2,79],"an":[3,26,51],"important":[4],"problem":[5],"in":[6],"natural":[7],"language":[8],"processing.":[9],"Most":[10],"of":[11,53],"previous":[12],"works":[13,75],"on":[14,34,67],"Vietnamese":[15,30],"word":[16,31],"are":[18],"supervised":[19],"learning.":[20,46],"In":[21,47],"this":[22],"paper,":[23],"we":[24,49],"propose":[25,50],"unsupervised":[27],"method":[28,74],"for":[29],"based":[33],"Hidden":[35],"Markov":[36],"Models.":[37],"We":[38],"naturally":[39],"encode":[40],"prior":[41],"linguistic":[42],"knowledge":[43],"into":[44],"model":[45],"decoding,":[48],"enhancement":[52],"Viterbi":[54],"decoding":[55],"algorithm":[56],"with":[57],"external":[58],"token":[59],"ordering":[60],"statistics":[61],"from":[62],"Pointwise":[63],"Mutual":[64],"Information.":[65],"Evaluation":[66],"benchmark":[68],"datasets":[69],"shows":[70],"that":[71],"the":[72],"proposed":[73],"reasonably":[76],"well.":[77],"Sourcecode":[78],"available":[80],"at":[81],"https://github.com/longbb/word_recognition":[82]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
