{"id":"https://openalex.org/W7160038668","doi":"https://doi.org/10.63317/58migi9wn3u6","title":"FreeTxt-Vi: A Benchmarked Vietnamese-English Toolkit for Segmentation, Sentiment, and Summarisation","display_name":"FreeTxt-Vi: A Benchmarked Vietnamese-English Toolkit for Segmentation, Sentiment, and Summarisation","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160038668","doi":"https://doi.org/10.63317/58migi9wn3u6"},"language":null,"primary_location":{"id":"doi:10.63317/58migi9wn3u6","is_oa":true,"landing_page_url":"https://doi.org/10.63317/58migi9wn3u6","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.516.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.516.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135126075","display_name":"Hung Viet Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung Huy Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093759946","display_name":"Mo El-Haj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]},{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB","VN"],"is_corresponding":false,"raw_author_name":"Mo El-Haj","raw_affiliation_strings":["Lancaster University , UK","VinUniversity , Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University , UK","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"VinUniversity , Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058785189","display_name":"Paul Rayson","orcid":"https://orcid.org/0000-0002-1257-2191"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Rayson","raw_affiliation_strings":["Lancaster University , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University , UK","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078509849","display_name":"Dawn Knight","orcid":"https://orcid.org/0000-0002-4745-6502"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dawn Knight","raw_affiliation_strings":["Cardiff University , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cardiff University , UK","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41516756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6509","last_page":"6518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.41440001130104065,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.41440001130104065,"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":0.16500000655651093,"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":0.12160000205039978,"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/feature","display_name":"Feature (linguistics)","score":0.2906000018119812},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2847000062465668},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.25380000472068787},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2531999945640564},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.24950000643730164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24950000643730164},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2493000030517578}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/58migi9wn3u6","is_oa":true,"landing_page_url":"https://doi.org/10.63317/58migi9wn3u6","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.516.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/58migi9wn3u6","is_oa":true,"landing_page_url":"https://doi.org/10.63317/58migi9wn3u6","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/pdf/2026.lrec2026-1.516.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160038668.pdf","grobid_xml":"https://content.openalex.org/works/W7160038668.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"FreeTxt-Vi":[0,111,158],"is":[1,73,112,180],"a":[2,77,84,94,100,115,122,171,183],"free":[3],"and":[4,10,22,33,55,66,99,129,131,149,162,194],"open-source":[5],"web-based":[6],"toolkit":[7,179],"for":[8,63,104,169],"creating":[9],"analysing":[11],"bilingual":[12,79],"Vietnamese-English":[13],"text":[14,108,156,200],"collections.Positioned":[15],"at":[16,209],"the":[17,74,164,195],"intersection":[18],"of":[19,70,76,117,166,186],"corpus":[20,44],"linguistics":[21],"natural":[23],"language":[24,118,167,176],"processing":[25,119],"(NLP),":[26],"it":[27],"enables":[28],"users":[29],"to":[30,142,154,182,207],"build,":[31],"explore,":[32],"interpret":[34],"free-text":[35],"data":[36,201],"without":[37],"requiring":[38],"programming":[39],"expertise.The":[40],"system":[41],"combines":[42],"established":[43],"analysis":[45,65,109],"features":[46],"such":[47],"as":[48,114],"concordancing,":[49],"keyword":[50],"analysis,":[51,128,157],"word":[52],"relation":[53],"exploration,":[54],"interactive":[56],"visualisation":[57],"with":[58],"modern":[59],"transformer-based":[60],"NLP":[61,80],"components":[62],"sentiment":[64,97,127],"summarisation.A":[67],"key":[68],"contribution":[69],"this":[71],"work":[72],"design":[75],"unified":[78],"pipeline":[81],"that":[82,133],"integrates":[83],"hybrid":[85],"VnCoreNLP":[86],"+":[87],"Byte":[88],"Pair":[89],"Encoding":[90],"(BPE)":[91],"segmentation":[92],"strategy,":[93],"fine-tuned":[95,101],"TabularisAI":[96],"classifier,":[98],"Qwen2.5":[102],"model":[103],"abstractive":[105],"summarisation.Unlike":[106],"existing":[107],"platforms,":[110],"evaluated":[113],"set":[116],"components.We":[120],"conduct":[121],"three-part":[123],"evaluation":[124],"covering":[125],"segmentation,":[126],"summarisation,":[130],"demonstrate":[132],"our":[134],"approach":[135],"achieves":[136],"competitive":[137],"or":[138],"superior":[139],"performance":[140],"compared":[141],"widely":[143,172],"used":[144],"baselines":[145],"in":[146,177],"both":[147],"Vietnamese":[148],"English.By":[150],"reducing":[151],"technical":[152],"barriers":[153],"multilingual":[155],"supports":[159],"reproducible":[160],"research":[161],"promotes":[163],"development":[165],"resources":[168],"Vietnamese,":[170],"spoken":[173],"but":[174,204],"underrepresented":[175],"NLP.The":[178],"applicable":[181],"wide":[184],"range":[185],"domains,":[187],"including":[188],"education,":[189],"digital":[190],"humanities,":[191],"cultural":[192],"heritage,":[193],"social":[196],"sciences,":[197],"where":[198],"qualitative":[199],"are":[202],"common":[203],"often":[205],"difficult":[206],"process":[208],"scale.":[210]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2026-05-05T00:00:00"}