{"id":"https://openalex.org/W4292773522","doi":"https://doi.org/10.1145/3548636.3548645","title":"Hybrid approach for text similarity detection in Vietnamese based on Sentence-BERT and WordNet","display_name":"Hybrid approach for text similarity detection in Vietnamese based on Sentence-BERT and WordNet","publication_year":2022,"publication_date":"2022-06-23","ids":{"openalex":"https://openalex.org/W4292773522","doi":"https://doi.org/10.1145/3548636.3548645"},"language":"en","primary_location":{"id":"doi:10.1145/3548636.3548645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548636.3548645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Information Technology and Computer Communications (ITCC)","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/A5067863948","display_name":"Son Cao","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":"Son Cao","raw_affiliation_strings":["University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112320937","display_name":"Huy Vo","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":"Huy Vo","raw_affiliation_strings":["University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076427684","display_name":"H\u1eb1ng L\u00ea Th\u1ecb Thu\u00fd","orcid":"https://orcid.org/0000-0001-8869-0736"},"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":"Hang Thi-Thuy Le","raw_affiliation_strings":["University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","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":"Dien Dinh","raw_affiliation_strings":["University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science, Vietnam and Vietnam National University - Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75217603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9966999888420105,"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/wordnet","display_name":"WordNet","score":0.9671076536178589},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.8741524815559387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257603645324707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7884634733200073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7493004202842712},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.670547366142273},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6246955990791321},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5979139804840088},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4539284110069275},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4132234752178192},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41280198097229004},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.274434357881546},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15635383129119873},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08733043074607849}],"concepts":[{"id":"https://openalex.org/C157659113","wikidata":"https://www.wikidata.org/wiki/Q533822","display_name":"WordNet","level":2,"score":0.9671076536178589},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8741524815559387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257603645324707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7884634733200073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7493004202842712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.670547366142273},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6246955990791321},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5979139804840088},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4539284110069275},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4132234752178192},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41280198097229004},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.274434357881546},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15635383129119873},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08733043074607849},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3548636.3548645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548636.3548645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 4th International Conference on Information Technology and Computer Communications (ITCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2045915373","https://openalex.org/W2100935296","https://openalex.org/W2117805756","https://openalex.org/W2242573961","https://openalex.org/W2508865106","https://openalex.org/W2534712034","https://openalex.org/W2896457183","https://openalex.org/W2898335012","https://openalex.org/W2912512851","https://openalex.org/W2970641574","https://openalex.org/W2983040767","https://openalex.org/W3007955273","https://openalex.org/W3197622744","https://openalex.org/W4247329683","https://openalex.org/W4287829760","https://openalex.org/W6764209848"],"related_works":["https://openalex.org/W2564015900","https://openalex.org/W2963829519","https://openalex.org/W2160266024","https://openalex.org/W2769116971","https://openalex.org/W1499795620","https://openalex.org/W3037446375","https://openalex.org/W2529667321","https://openalex.org/W2791526418","https://openalex.org/W1596052364","https://openalex.org/W2129510087"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,61],"explore":[4],"the":[5,16,20,51],"task":[6,21],"of":[7],"similarity":[8],"detection,":[9],"which":[10],"determines":[11],"whether":[12],"two":[13,66],"sentences":[14],"have":[15],"same":[17],"meaning.":[18],"Although":[19],"has":[22,36],"shown":[23],"to":[24],"be":[25],"important":[26],"in":[27,39],"many":[28],"natural":[29],"language":[30],"processing":[31],"applications,":[32],"not":[33],"much":[34],"work":[35],"been":[37],"done":[38],"Vietnamese.":[40],"We":[41],"present":[42],"an":[43],"approach":[44],"based":[45],"on":[46,65,80,86],"Sentence-BERT":[47],"(SBERT)":[48],"model.":[49],"Leveraging":[50],"pre-trained":[52],"model":[53,75],"and":[54,71,82],"combining":[55],"it":[56,64],"with":[57],"linguistic":[58],"knowledge":[59],"(WordNet),":[60],"then":[62],"tested":[63],"popular":[67],"Vietnamese":[68],"datasets:":[69],"vnPara":[70,81],"VNPC.":[72,87],"Our":[73],"best":[74],"achieves":[76],"97.62%":[77],"F1":[78,84],"score":[79,85],"95.31%":[83]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}