{"id":"https://openalex.org/W4408811769","doi":"https://doi.org/10.1145/3725848","title":"LatVis: Large-scale Task-specific Language Model for Low-resource Vietnamese Multi-document Summarization","display_name":"LatVis: Large-scale Task-specific Language Model for Low-resource Vietnamese Multi-document Summarization","publication_year":2025,"publication_date":"2025-03-25","ids":{"openalex":"https://openalex.org/W4408811769","doi":"https://doi.org/10.1145/3725848"},"language":"en","primary_location":{"id":"doi:10.1145/3725848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725848","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725848","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061069106","display_name":"The Anh Le","orcid":"https://orcid.org/0000-0003-0740-6380"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]},{"id":"https://openalex.org/I177733328","display_name":"Can Tho University","ror":"https://ror.org/0071qz696","country_code":"VN","type":"education","lineage":["https://openalex.org/I177733328"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"The Anh Le","raw_affiliation_strings":["FPT University, Can Tho Campus, Can Tho, Vietnam","Department of Information Technology, FPT University, Can Tho Campus, Can Tho, Viet Nam"],"raw_orcid":"https://orcid.org/0000-0003-0740-6380","affiliations":[{"raw_affiliation_string":"FPT University, Can Tho Campus, Can Tho, Vietnam","institution_ids":["https://openalex.org/I177733328","https://openalex.org/I109689652"]},{"raw_affiliation_string":"Department of Information Technology, FPT University, Can Tho Campus, Can Tho, Viet Nam","institution_ids":["https://openalex.org/I177733328","https://openalex.org/I109689652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111386493","display_name":"Hai Son Le","orcid":"https://orcid.org/0009-0003-2240-0451"},"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":"Hai Son Le","raw_affiliation_strings":["Hanoi University of Science and Technology, Hanoi, Vietnam","Computer Science, Hanoi University of Science and Technology, Hanoi, Viet Nam"],"raw_orcid":"https://orcid.org/0009-0003-2240-0451","affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]},{"raw_affiliation_string":"Computer Science, Hanoi University of Science and Technology, Hanoi, Viet Nam","institution_ids":["https://openalex.org/I94518387"]}]}],"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":0.02249387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"5","first_page":"1","last_page":"19"},"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":0.9991999864578247,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/automatic-summarization","display_name":"Automatic summarization","score":0.910578727722168},{"id":"https://openalex.org/keywords/vietnamese","display_name":"Vietnamese","score":0.8316663503646851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6809146404266357},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5886637568473816},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5197034478187561},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5076502561569214},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4498875141143799},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.41118913888931274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36570310592651367},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2661147117614746},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1259549856185913},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10061657428741455}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.910578727722168},{"id":"https://openalex.org/C103621254","wikidata":"https://www.wikidata.org/wiki/Q9199","display_name":"Vietnamese","level":2,"score":0.8316663503646851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809146404266357},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5886637568473816},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5197034478187561},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5076502561569214},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4498875141143799},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.41118913888931274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36570310592651367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2661147117614746},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1259549856185913},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10061657428741455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725848","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3725848","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725848","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725848","source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408811769.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2121522511","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2963979492","https://openalex.org/W2964028111","https://openalex.org/W2970419734","https://openalex.org/W2981852735","https://openalex.org/W3012910066","https://openalex.org/W3034961030","https://openalex.org/W3034999214","https://openalex.org/W3035050380","https://openalex.org/W3037976772","https://openalex.org/W3098637735","https://openalex.org/W3169250374","https://openalex.org/W3199323859","https://openalex.org/W3210390771","https://openalex.org/W4280557512","https://openalex.org/W4285171765","https://openalex.org/W4288089799","https://openalex.org/W4305039137"],"related_works":["https://openalex.org/W3164984162","https://openalex.org/W2104677027","https://openalex.org/W2902627734","https://openalex.org/W2112885393","https://openalex.org/W2065541085","https://openalex.org/W2785821657","https://openalex.org/W2173208124","https://openalex.org/W2568827738","https://openalex.org/W1990695371","https://openalex.org/W2365100044"],"abstract_inverted_index":{"The":[0],"Vietnamese":[1,90,106,182],"multi-document":[2,97,183],"summarization":[3],"task":[4],"faces":[5],"three":[6],"key":[7],"challenges":[8,37],"including":[9],"the":[10,19,36,74,118,157,164,171,181,188],"long":[11,40],"input":[12,41],"sequence":[13],"problem,":[14],"human-like":[15],"summary":[16],"generation,":[17,57],"and":[18,31,143,148,151],"scarcity":[20,75],"of":[21,76,88,140,166,190],"labeled":[22,77],"data.":[23,78],"Transformer-based":[24],"models,":[25],"enhanced":[26],"by":[27,39],"parallel":[28],"computation":[29],"architectures":[30],"attention":[32],"mechanisms,":[33],"partially":[34],"mitigate":[35],"posed":[38],"sequences.":[42],"Additionally,":[43],"when":[44],"trained":[45],"on":[46,80,131,156],"large-scale":[47,95,174],"text":[48,56,91],"corpora,":[49],"these":[50,81],"models":[51,193],"achieve":[52],"impressive":[53],"performance":[54,123],"in":[55],"approaching":[58],"human-level":[59],"performance.":[60],"Furthermore,":[61],"pre-training":[62],"with":[63],"self-supervised":[64],"learning":[65],"objectives":[66],"is":[67,100,170],"an":[68],"effective":[69],"strategy":[70],"to":[71,92,103,125],"compensate":[72],"for":[73,145,153,180,194,199],"Based":[79],"considerations,":[82],"this":[83,169],"article":[84],"leverages":[85],"large":[86],"corpora":[87],"unlabeled":[89],"build":[93],"a":[94,105],"pseudo-labeled":[96],"dataset,":[98],"which":[99],"then":[101],"used":[102],"pre-train":[104],"task-specific":[107,175,191],"language":[108,176,192,197],"model,":[109],"LatVis.":[110],"Experimental":[111],"results":[112],"demonstrate":[113],"that,":[114],"even":[115],"without":[116],"fine-tuning,":[117],"pre-trained":[119,178],"model":[120,177],"achieves":[121],"competitive":[122],"compared":[124],"several":[126],"previous":[127],"models.":[128],"After":[129],"fine-tuning":[130],"approximately":[132],"300":[133],"samples,":[134],"LatVis":[135],"obtains":[136],"notable":[137],"Rouge":[138],"Scores":[139],"76.7%,":[141],"78.9%,":[142],"73.9%":[144],"Rouge-1":[146],"F1,":[147],"50.2%,":[149],"55.0%,":[150],"46.7%":[152],"Rouge-2":[154],"F1":[155],"VMDS,":[158],"ViMS,":[159],"VLSP":[160],"datasets,":[161],"respectively.":[162],"To":[163],"best":[165],"our":[167],"knowledge,":[168],"first":[172],"publicly":[173],"specifically":[179],"summarization.":[184],"This":[185],"work":[186],"highlights":[187],"potential":[189],"advancing":[195],"natural":[196],"processing":[198],"low-resource":[200],"languages.":[201]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
