{"id":"https://openalex.org/W2165142900","doi":"https://doi.org/10.1109/rivf.2006.1696447","title":"A maximum entropy approach for vietnamese word segmentation","display_name":"A maximum entropy approach for vietnamese word segmentation","publication_year":2006,"publication_date":"2006-09-22","ids":{"openalex":"https://openalex.org/W2165142900","doi":"https://doi.org/10.1109/rivf.2006.1696447","mag":"2165142900"},"language":"en","primary_location":{"id":"doi:10.1109/rivf.2006.1696447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2006.1696447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 International Conference onResearch, Innovation and Vision for the Future","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040236875","display_name":"\u0110i\u1ec1n \u0110inh","orcid":"https://orcid.org/0000-0003-2069-1016"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh Dien","raw_affiliation_strings":["Faculty of Information Technology, University of Natural Sciences, Vietnam National University, Ho Chi Minh, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Natural Sciences, Vietnam National University, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051050864","display_name":"Vu Viet Thuy","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Vu Thuy","raw_affiliation_strings":["Faculty of Information Technology, University of Natural Sciences, Vietnam National University, Ho Chi Minh, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, University of Natural Sciences, Vietnam National University, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":3.4198,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93637675,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"248","last_page":"253"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9955999851226807,"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":0.7548720836639404},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6520923376083374},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6476665735244751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6470532417297363},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6218584775924683},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.5692971348762512},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5616647005081177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5613878965377808},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5236218571662903},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5199136137962341},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49705222249031067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3636879324913025},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1610957384109497},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07590681314468384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548720836639404},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6520923376083374},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6476665735244751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6470532417297363},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6218584775924683},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.5692971348762512},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5616647005081177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5613878965377808},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5236218571662903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5199136137962341},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49705222249031067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3636879324913025},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1610957384109497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07590681314468384},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf.2006.1696447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rivf.2006.1696447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 International Conference onResearch, Innovation and Vision for the Future","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W14712889","https://openalex.org/W1773803948","https://openalex.org/W2001792610","https://openalex.org/W2033295622","https://openalex.org/W2163377725","https://openalex.org/W2165142900","https://openalex.org/W3145501851","https://openalex.org/W6683955732"],"related_works":["https://openalex.org/W2901286616","https://openalex.org/W2291461084","https://openalex.org/W2050882094","https://openalex.org/W3113733647","https://openalex.org/W4206924063","https://openalex.org/W3042674643","https://openalex.org/W2946128423","https://openalex.org/W2918555272","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"In":[0],"this":[1,83],"paper,":[2],"we":[3,64],"introduce":[4],"a":[5,69,77],"new":[6],"approach":[7,84],"for":[8,72,87],"Vietnamese":[9,88],"Word":[10,89],"Segmentation.":[11,90],"The":[12,42,74,91],"word":[13],"segmentation":[14],"problem":[15],"is":[16,85],"restated":[17],"into":[18,68],"the":[19,27,31,39,45,53,56,60,104],"morpho-syllable":[20],"position-in-word":[21],"(PIW)":[22],"tagging":[23],"problem.":[24],"We":[25],"used":[26,49],"Maximum":[28],"Entropy":[29],"with":[30],"Generalized":[32],"Iterative":[33],"Scaling":[34],"(GIS)":[35],"to":[36,50],"train":[37],"on":[38,76],"annotated":[40],"corpora.":[41],"result":[43],"of":[44,55,79,98,106],"training":[46],"process":[47],"was":[48],"tag":[51],"all":[52],"morpho-syllables":[54],"input":[57],"sentence.":[58],"With":[59],"output":[61],"sentence":[62,71],"tagged,":[63],"can":[65],"convert":[66],"it":[67],"segmented":[70],"evaluation.":[73],"results":[75],"lot":[78],"tagged-corpora":[80],"show":[81],"that":[82],"suitable":[86],"performance":[92],"achieves":[93],"precision":[94],"and":[95,100,103],"recall":[96],"rates":[97],"94.87%":[99],"94.08%":[101],"respectively,":[102],"F-measure":[105],"94.44%.":[107],"Index":[108],"Terms\u2014word":[109],"segmentation,":[110],"maximum":[111],"entropy":[112]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}