{"id":"https://openalex.org/W4393066111","doi":"https://doi.org/10.1109/rivf60135.2023.10471791","title":"An Empirical Study of Information Extraction from Vietnamese Documents","display_name":"An Empirical Study of Information Extraction from Vietnamese Documents","publication_year":2023,"publication_date":"2023-12-23","ids":{"openalex":"https://openalex.org/W4393066111","doi":"https://doi.org/10.1109/rivf60135.2023.10471791"},"language":"en","primary_location":{"id":"doi:10.1109/rivf60135.2023.10471791","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rivf60135.2023.10471791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5052518798","display_name":"Lam Thanh Nguyen","orcid":"https://orcid.org/0000-0002-3413-8281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam Nguyen","raw_affiliation_strings":["CMC Applied Technology Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101801900","display_name":"Tien-Dong Nguyen","orcid":"https://orcid.org/0000-0001-5563-0358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien-Dong Nguyen","raw_affiliation_strings":["CMC Applied Technology Institute","CMC University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]},{"raw_affiliation_string":"CMC University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054245944","display_name":"Minh-Tuan Dang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150999","display_name":"Research Institute of Posts and Telecommunications","ror":"https://ror.org/04j808v60","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4210150999"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Minh-Tuan Dang","raw_affiliation_strings":["CMC Applied Technology Institute","Posts and Telecommunications Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]},{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology","institution_ids":["https://openalex.org/I4210150999","https://openalex.org/I4400600977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102633766","display_name":"Dinh-Nguyen Vu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinh-Nguyen Vu","raw_affiliation_strings":["CMC Applied Technology Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100509222","display_name":"Viet-Anh Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet-Anh Nguyen","raw_affiliation_strings":["CMC Applied Technology Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101321620","display_name":"Hoang-Dang Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoang-Dang Nguyen","raw_affiliation_strings":["CMC Applied Technology Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMC Applied Technology Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21612009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"539","last_page":"544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8543999791145325,"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":0.8543999791145325,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.8442000150680542,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.8264999985694885,"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/vietnamese","display_name":"Vietnamese","score":0.8693610429763794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845943927764893},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5403696298599243},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5000147819519043},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08794739842414856}],"concepts":[{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8693610429763794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845943927764893},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5403696298599243},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5000147819519043},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08794739842414856},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf60135.2023.10471791","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rivf60135.2023.10471791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2012210378","https://openalex.org/W2095818033","https://openalex.org/W2106571683","https://openalex.org/W2163113711","https://openalex.org/W2785886262","https://openalex.org/W2891117443","https://openalex.org/W2896457183","https://openalex.org/W2907101105","https://openalex.org/W2922714365","https://openalex.org/W2947697927","https://openalex.org/W2964015378","https://openalex.org/W2986619406","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3021709838","https://openalex.org/W3104953317","https://openalex.org/W3163650427","https://openalex.org/W4285819076","https://openalex.org/W6738964360"],"related_works":["https://openalex.org/W2748952813","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/W1844055093","https://openalex.org/W61780229","https://openalex.org/W2077055222"],"abstract_inverted_index":{"Information":[0],"Extraction":[1],"(IE)":[2],"is":[3,14],"the":[4,31,68,72,85,90,117,142],"procedure":[5],"of":[6,35,42,49,64,84,92,106,137,144],"transforming":[7],"unstructured":[8],"data":[9,33],"into":[10],"structured":[11],"formats.":[12],"IE":[13,88,113,124],"vital":[15],"to":[16,54,71],"many":[17],"document":[18],"intelligence":[19],"applications":[20],"and":[21,111,131,140],"has":[22,51],"high":[23],"potential":[24],"in":[25,147],"business":[26],"as":[27,127],"it":[28],"can":[29],"automate":[30],"manual":[32],"extraction":[34,57],"all":[36,136],"required":[37],"information":[38,56],"from":[39],"various":[40],"kinds":[41],"documents.":[43],"However,":[44],"although":[45],"a":[46,81,98],"substantial":[47],"amount":[48],"research":[50],"been":[52],"done":[53],"develop":[55],"approaches":[58],"using":[59,122],"deep":[60],"learning":[61],"models,":[62],"none":[63],"these":[65,138],"have":[66],"applied":[67],"proposed":[69],"methods":[70,139],"Vietnamese":[73,99],"documents":[74],"domain.":[75],"In":[76],"this":[77,93,120,148],"study,":[78],"we":[79],"provide":[80],"comprehensive":[82],"review":[83],"literature":[86],"on":[87,119,135],"at":[89],"time":[91],"writing.":[94],"We":[95,115],"also":[96],"propose":[97],"Visually":[100],"Rich":[101],"Document":[102],"(VRD)":[103],"benchmark":[104,121],"consisting":[105],"input":[107],"images,":[108],"text":[109],"contents,":[110],"corresponding":[112],"labels.":[114],"verify":[116],"applicability":[118],"multiple":[123],"models":[125],"such":[126],"(MSAU,":[128],"LayoutLM,":[129],"GNN)":[130],"show":[132],"strong":[133],"results":[134],"evaluate":[141],"capabilities":[143],"each":[145],"model":[146],"dataset.":[149]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}