{"id":"https://openalex.org/W3091697477","doi":"https://doi.org/10.21437/interspeech.2020-1896","title":"Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models","display_name":"Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3091697477","doi":"https://doi.org/10.21437/interspeech.2020-1896","mag":"3091697477"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1896","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.00198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044152577","display_name":"Thai Binh Nguyen","orcid":"https://orcid.org/0009-0008-8100-6338"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thai Binh Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691795","display_name":"Quang Minh Nguyen","orcid":"https://orcid.org/0000-0003-2951-8332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quang Minh Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695332","display_name":"Thi Thu Hien Nguyen","orcid":"https://orcid.org/0000-0001-7726-3034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thi Thu Hien Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102847246","display_name":"Quoc Truong","orcid":"https://orcid.org/0000-0003-1472-1370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052741228","display_name":"Chi Mai Luong","orcid":"https://orcid.org/0000-0002-2559-2247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi Mai Luong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044152577"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12409185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4263","last_page":"4267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9975000023841858,"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/punctuation","display_name":"Punctuation","score":0.8659811019897461},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.833191990852356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7928283214569092},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7024927735328674},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.6561463475227356},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6279870867729187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6040497422218323},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.5366238355636597},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.5329502820968628},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.532520592212677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4751743674278259},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.29110467433929443}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.8659811019897461},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.833191990852356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7928283214569092},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7024927735328674},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.6561463475227356},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6279870867729187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6040497422218323},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.5366238355636597},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5329502820968628},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.532520592212677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4751743674278259},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29110467433929443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1896","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.00198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00198","pdf_url":"https://arxiv.org/pdf/2010.00198","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3091697477","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.00198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.00198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.00198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.00198","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00198","pdf_url":"https://arxiv.org/pdf/2010.00198","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3091697477.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W61030608","https://openalex.org/W75790607","https://openalex.org/W124954147","https://openalex.org/W146093233","https://openalex.org/W156633441","https://openalex.org/W1524333225","https://openalex.org/W1934019294","https://openalex.org/W1976339715","https://openalex.org/W2004384146","https://openalex.org/W2009774589","https://openalex.org/W2011084371","https://openalex.org/W2045993505","https://openalex.org/W2068882115","https://openalex.org/W2134426579","https://openalex.org/W2141099517","https://openalex.org/W2158188757","https://openalex.org/W2158899491","https://openalex.org/W2163918411","https://openalex.org/W2166116787","https://openalex.org/W2251857158","https://openalex.org/W2295407839","https://openalex.org/W2398104528","https://openalex.org/W2406932913","https://openalex.org/W2407834842","https://openalex.org/W2857028992","https://openalex.org/W2921532028","https://openalex.org/W2922722434","https://openalex.org/W2933138175","https://openalex.org/W2962989741","https://openalex.org/W2963979075","https://openalex.org/W2965373594","https://openalex.org/W2993229155","https://openalex.org/W2998802242","https://openalex.org/W3011222885"],"related_works":["https://openalex.org/W3095073040","https://openalex.org/W2147228869","https://openalex.org/W2431971047","https://openalex.org/W2785734129","https://openalex.org/W2911313899","https://openalex.org/W2088253551","https://openalex.org/W1127114108","https://openalex.org/W2899134946","https://openalex.org/W2134591869","https://openalex.org/W2130616163","https://openalex.org/W1976448505","https://openalex.org/W2010910318","https://openalex.org/W3161760609","https://openalex.org/W2139309347","https://openalex.org/W840590170","https://openalex.org/W2404544250","https://openalex.org/W3207836786","https://openalex.org/W1569479091","https://openalex.org/W2899879954","https://openalex.org/W2155072375"],"abstract_inverted_index":{"Studies":[0],"on":[1,16],"the":[2,39,44,56,61,70,80,92,96,107,125,140,156,173],"Named":[3],"Entity":[4],"Recognition":[5],"(NER)":[6],"task":[7,99,120],"have":[8],"shown":[9],"outstanding":[10],"results":[11,170],"that":[12,55,90,123,163,172],"reach":[13],"human":[14],"parity":[15],"input":[17,40,145],"texts":[18],"with":[19,25],"correct":[20],"text":[21,45,62,126,132,146,161],"formattings,":[22],"such":[23,31],"as":[24],"proper":[26,160],"punctuation":[27,135],"and":[28,54,78,134,151],"capitalization.":[29],"However,":[30],"conditions":[32],"are":[33],"not":[34,59],"available":[35],"in":[36],"applications":[37],"where":[38],"is":[41,46],"speech,":[42],"because":[43],"generated":[47],"from":[48,121,147],"a":[49,115,131],"speech":[50,73,122],"recognition":[51],"system":[52,57,150],"(ASR),":[53],"does":[58],"consider":[60],"formatting.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,113],"(1)":[68],"presented":[69],"first":[71,81],"Vietnamese":[72,89,97],"dataset":[74],"for":[75,88,95,118],"NER":[76,98,119,167],"task,":[77],"(2)":[79],"pre-trained":[82],"public":[83],"large-scale":[84],"monolingual":[85],"language":[86],"model":[87,137,143,175],"achieved":[91],"new":[93,116],"state-of-the-art":[94],"by":[100,129,179],"1.3%":[101],"absolute":[102],"F1":[103],"score":[104],"comparing":[105],"to":[106,165,177],"latest":[108],"study.":[109],"And":[110],"finally,":[111],"(3)":[112],"proposed":[114],"pipeline":[117],"overcomes":[124],"formatting":[127,162],"problem":[128],"introducing":[130],"capitalization":[133],"recovery":[136],"(CaPu)":[138],"into":[139],"pipeline.":[141],"The":[142],"takes":[144],"an":[148],"ASR":[149],"performs":[152],"two":[153],"tasks":[154],"at":[155],"same":[157],"time,":[158],"producing":[159],"helps":[164,176],"improve":[166,178],"performance.":[168],"Experimental":[169],"indicated":[171],"CaPu":[174],"nearly":[180],"4%":[181],"of":[182],"F1-score.":[183]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}