{"id":"https://openalex.org/W2969257556","doi":"https://doi.org/10.1145/3342827.3342851","title":"A Hybrid Method for Vietnamese Text Normalization","display_name":"A Hybrid Method for Vietnamese Text Normalization","publication_year":2019,"publication_date":"2019-06-28","ids":{"openalex":"https://openalex.org/W2969257556","doi":"https://doi.org/10.1145/3342827.3342851","mag":"2969257556"},"language":"en","primary_location":{"id":"doi:10.1145/3342827.3342851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342827.3342851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","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/A5101435787","display_name":"Nguy\u1ec5n Th\u1ecb Thu Trang","orcid":"https://orcid.org/0000-0002-5015-082X"},"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":true,"raw_author_name":"Nguyen Thi Thu Trang","raw_affiliation_strings":["VBee Group, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"VBee Group, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059732351","display_name":"Dang Xuan Bach","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":"Dang Xuan Bach","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101748259","display_name":"Nguyen Xuan Tung","orcid":"https://orcid.org/0000-0003-3992-7746"},"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":"Nguyen Xuan Tung","raw_affiliation_strings":["VBee Group, Hanoi University of Science and Technology, Hanoi, Vietnam"],"affiliations":[{"raw_affiliation_string":"VBee Group, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101435787"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77988267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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":0.9976000189781189,"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/vietnamese","display_name":"Vietnamese","score":0.7425082921981812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354817390441895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6670514941215515},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6658182740211487},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6486878395080566},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6347867846488953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6233087778091431},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4884999990463257},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4739943742752075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3501681089401245},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1468992531299591}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.7425082921981812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354817390441895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6670514941215515},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6658182740211487},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6486878395080566},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6347867846488953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6233087778091431},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4739943742752075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3501681089401245},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1468992531299591},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342827.3342851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342827.3342851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W2063178951","https://openalex.org/W2133564696","https://openalex.org/W2747175885","https://openalex.org/W2748939531","https://openalex.org/W2749051922","https://openalex.org/W2776429271","https://openalex.org/W2807022326","https://openalex.org/W2921558328","https://openalex.org/W2949888546","https://openalex.org/W6755438825"],"related_works":["https://openalex.org/W4249825331","https://openalex.org/W4322096459","https://openalex.org/W2069349846","https://openalex.org/W2273320598","https://openalex.org/W2136292188","https://openalex.org/W3169653581","https://openalex.org/W4287236229","https://openalex.org/W4287393888","https://openalex.org/W2346079336","https://openalex.org/W4287829760"],"abstract_inverted_index":{"This":[0,179],"paper":[1],"presents":[2],"a":[3,23,29,62,84,91,97,160,172],"hybrid":[4,63],"method":[5],"for":[6,115,125,165,169,174],"normalizing":[7],"written":[8],"text":[9,21],"often":[10],"found":[11],"on":[12,54,96],"newspapers":[13],"to":[14,50],"its":[15],"spoken":[16],"form.":[17],"To":[18],"normalize":[19],"raw":[20],"with":[22,100,129,145,171],"number":[24],"of":[25,66,77,110,143,163,186],"non-standard":[26],"words":[27],"(NSWs),":[28],"two-step":[30],"model":[31,89,113,132,138,158,180],"is":[32,49],"proposed.":[33],"The":[34,46,94,136],"first":[35],"step":[36],"involves":[37],"classifying":[38],"NSWs":[39],"into":[40,58,122],"different":[41],"categories":[42,103],"using":[43,61],"Random":[44],"Forest.":[45],"latter":[47,127],"one":[48,123],"expand":[51],"them,":[52],"depending":[53],"their":[55],"NSW":[56,102],"types,":[57,119],"pronounceable":[59],"syllables":[60],"method.":[64],"Most":[65],"numeric":[67],"types":[68],"can":[69,181],"be":[70,81],"expanded":[71,82],"by":[72,83],"well-defined":[73],"rules":[74],"while":[75],"most":[76,107],"alphabetic":[78],"ones":[79],"must":[80],"deep":[85],"learning":[86],"(i.e.":[87],"sequence-to-sequence)":[88],"and":[90,117,133,149,167],"post":[92],"adjustment.":[93],"experiment":[95],"Vietnamese":[98],"corpus":[99],"proposed":[101],"shows":[104,159],"that":[105],"the":[106,111,126,146,150,154,156,184],"ambiguous":[108],"cases":[109],"classification":[112,137],"are":[114],"abbreviation":[116],"read-as-sequence":[118],"hence":[120],"combined":[121],"category":[124,147],"expansion":[128],"more":[130],"complex":[131],"better":[134],"context.":[135,189],"gives":[139],"an":[140],"enhanced":[141],"result":[142,162],"99.20%":[144],"combination":[148],"feature":[151],"optimization.":[152],"In":[153],"expansion,":[155],"sequence-to-sequence":[157],"good":[161],"96.53%":[164],"abbreviations":[166,187],"96.25%":[168],"loanwords":[170],"post-adjustment":[173],"some":[175],"completely":[176],"wrong":[177],"cases.":[178],"predict":[182],"effectively":[183],"expansions":[185],"in":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}