{"id":"https://openalex.org/W2995082385","doi":"https://doi.org/10.1145/3368926.3369716","title":"Punctuation Prediction for Vietnamese Texts Using Conditional Random Fields","display_name":"Punctuation Prediction for Vietnamese Texts Using Conditional Random Fields","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2995082385","doi":"https://doi.org/10.1145/3368926.3369716","mag":"2995082385"},"language":"en","primary_location":{"id":"doi:10.1145/3368926.3369716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology - SoICT 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/sis_research/7816","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041295441","display_name":"Quang Pham","orcid":"https://orcid.org/0000-0002-6416-5328"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Quang H. Pham","raw_affiliation_strings":["School of Information System, Singapore Management University"],"affiliations":[{"raw_affiliation_string":"School of Information System, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103749527","display_name":"Binh Thanh Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Binh T. Nguyen","raw_affiliation_strings":["AISIA Research Lab, VNU HCM - University of Science"],"affiliations":[{"raw_affiliation_string":"AISIA Research Lab, VNU HCM - University of Science","institution_ids":["https://openalex.org/I23582244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050413008","display_name":"Cuong Viet Nguyen","orcid":"https://orcid.org/0000-0002-6803-3488"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nguyen Viet Cuong","raw_affiliation_strings":["Department of Engineering, University of Cambridge"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041295441"],"corresponding_institution_ids":["https://openalex.org/I79891267"],"apc_list":null,"apc_paid":null,"fwci":0.434,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73165138,"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":"322","last_page":"327"},"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.9968000054359436,"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/punctuation","display_name":"Punctuation","score":0.9597145915031433},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.9412553310394287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8225913047790527},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.679654598236084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6620233654975891},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6277807354927063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6257535219192505},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5793302059173584},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5486867427825928},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.47213393449783325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35698503255844116},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10403433442115784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0769064724445343}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9597145915031433},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.9412553310394287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225913047790527},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.679654598236084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6620233654975891},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6277807354927063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6257535219192505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5793302059173584},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5486867427825928},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.47213393449783325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35698503255844116},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10403433442115784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0769064724445343},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3368926.3369716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368926.3369716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Information and Communication Technology - SoICT 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-8819","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/7816","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3368926.3369716","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-8819","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/7816","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3368926.3369716","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W14712889","https://openalex.org/W27634986","https://openalex.org/W94670513","https://openalex.org/W1532325895","https://openalex.org/W1766290689","https://openalex.org/W2113851376","https://openalex.org/W2125838338","https://openalex.org/W2137100725","https://openalex.org/W2137357063","https://openalex.org/W2141099517","https://openalex.org/W2147228869","https://openalex.org/W2147880316","https://openalex.org/W2156515921","https://openalex.org/W2165073960","https://openalex.org/W2166116787","https://openalex.org/W2406343628","https://openalex.org/W2407834842","https://openalex.org/W2917807695"],"related_works":["https://openalex.org/W2962906565","https://openalex.org/W2798423868","https://openalex.org/W3027026357","https://openalex.org/W3015678144","https://openalex.org/W2061027419","https://openalex.org/W2076440176","https://openalex.org/W3126392069","https://openalex.org/W2109665237","https://openalex.org/W2944198262","https://openalex.org/W3136048405"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,6,55,62],"punctuation":[3,21],"prediction":[4],"for":[5,37,60,74,120],"Vietnamese":[7,82],"language.":[8],"This":[9],"problem":[10,63,116],"is":[11,117],"crucial":[12],"as":[13,46],"it":[14],"can":[15,126],"be":[16],"used":[17],"to":[18,23,34,100,132],"add":[19],"suitable":[20],"marks":[22],"machine-transcribed":[24],"speeches,":[25],"which":[26],"usually":[27],"do":[28],"not":[29],"have":[30],"such":[31],"information.":[32],"Similar":[33],"previous":[35],"works":[36],"English":[38],"and":[39,64,85,88,123],"Chinese":[40],"languages,":[41],"we":[42,53,77,96],"formulate":[43],"this":[44,115],"task":[45],"a":[47,66,104,121,133],"sequence":[48],"labeling":[49],"problem.":[50],"After":[51],"that,":[52],"apply":[54],"conditional":[56],"random":[57],"field":[58],"model":[59,125],"solving":[61],"propose":[65],"set":[67],"of":[68,107],"appropriate":[69],"features":[70],"that":[71,114],"are":[72],"useful":[73],"prediction.":[75],"Moreover,":[76],"build":[78],"two":[79],"corpora":[80],"from":[81],"online":[83],"news":[84],"movie":[86],"subtitles":[87],"perform":[89],"extensive":[90],"experiments":[91],"on":[92],"these":[93],"data.":[94],"Finally,":[95],"ask":[97],"four":[98],"volunteers":[99],"insert":[101],"punctuations":[102],"into":[103],"small":[105],"sample":[106],"our":[108,124],"dataset.":[109],"The":[110],"experimental":[111],"results":[112],"show":[113],"challenging,":[118],"even":[119],"human,":[122],"achieve":[127],"near":[128],"performance":[129],"in":[130],"comparison":[131],"human.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}