{"id":"https://openalex.org/W7108320567","doi":"https://doi.org/10.5753/eniac.2025.13966","title":"Efficient Compression-Based Low-resource Text Classification","display_name":"Efficient Compression-Based Low-resource Text Classification","publication_year":2025,"publication_date":"2025-09-29","ids":{"openalex":"https://openalex.org/W7108320567","doi":"https://doi.org/10.5753/eniac.2025.13966"},"language":"en","primary_location":{"id":"doi:10.5753/eniac.2025.13966","doi":"https://doi.org/10.5753/eniac.2025.13966","is_oa":true,"landing_page_url":"https://doi.org/10.5753/eniac.2025.13966","pdf_url":"https://sol.sbc.org.br/index.php/eniac/article/download/38854/38627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXII Encontro Nacional de Intelig\u00eancia Artificial e Computacional (ENIAC 2025)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://sol.sbc.org.br/index.php/eniac/article/download/38854/38627","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bruno Vargas de Souza","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Vargas de Souza","raw_affiliation_strings":["UnB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UnB","institution_ids":["https://openalex.org/I150729083"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pedro Garcia Freitas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150729083","display_name":"Universidade de Bras\u00edlia","ror":"https://ror.org/02xfp8v59","country_code":"BR","type":"education","lineage":["https://openalex.org/I150729083"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Pedro Garcia Freitas","raw_affiliation_strings":["UnB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UnB","institution_ids":["https://openalex.org/I150729083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150729083"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1797","last_page":"1808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8047000169754028,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8047000169754028,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.13850000500679016,"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":0.025599999353289604,"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/text-classification","display_name":"text classification","score":0.9010000228881836},{"id":"https://openalex.org/keywords/low-resource-classification","display_name":"low-resource classification","score":0.6850000023841858},{"id":"https://openalex.org/keywords/k-nearest-neighbors","display_name":"k-nearest neighbors","score":0.9620000123977661},{"id":"https://openalex.org/keywords/compressed-data","display_name":"compressed data","score":0.515999972820282},{"id":"https://openalex.org/keywords/similarity-search","display_name":"similarity search","score":0.9300000071525574},{"id":"https://openalex.org/keywords/compression-algorithms","display_name":"compression algorithms","score":0.7089999914169312},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.6330000162124634},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553600013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5094000101089478},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5073999762535095},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C56289965","wikidata":"https://www.wikidata.org/wiki/Q5249246","display_name":"Decision tree model","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/eniac.2025.13966","doi":"https://doi.org/10.5753/eniac.2025.13966","is_oa":true,"landing_page_url":"https://doi.org/10.5753/eniac.2025.13966","pdf_url":"https://sol.sbc.org.br/index.php/eniac/article/download/38854/38627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXII Encontro Nacional de Intelig\u00eancia Artificial e Computacional (ENIAC 2025)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5753/eniac.2025.13966","doi":"https://doi.org/10.5753/eniac.2025.13966","is_oa":true,"landing_page_url":"https://doi.org/10.5753/eniac.2025.13966","pdf_url":"https://sol.sbc.org.br/index.php/eniac/article/download/38854/38627","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anais do XXII Encontro Nacional de Intelig\u00eancia Artificial e Computacional (ENIAC 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7108320567.pdf","grobid_xml":"https://content.openalex.org/works/W7108320567.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1490796714","https://openalex.org/W1994529543","https://openalex.org/W2034190452","https://openalex.org/W2066792529","https://openalex.org/W2171886309","https://openalex.org/W2903638214","https://openalex.org/W3084651990","https://openalex.org/W4385571422"],"related_works":["https://openalex.org/W4385571422","https://openalex.org/W4405433117","https://openalex.org/W4312051751","https://openalex.org/W7202408253","https://openalex.org/W4307206896","https://openalex.org/W4298226315","https://openalex.org/W1953638699","https://openalex.org/W7131791987","https://openalex.org/W3048215350","https://openalex.org/W2964258799"],"abstract_inverted_index":{"In":[0,88],"recent":[1,50],"years,":[2],"the":[3,106,114,116,134,162],"machine":[4],"learning":[5],"community":[6],"has":[7],"engaged":[8],"on":[9,52,78,108],"training":[10,86],"increasingly":[11],"powerful":[12],"large":[13],"language":[14],"models":[15,74],"(LLMs)":[16],"for":[17,56,102,133],"text":[18,57],"classification":[19,58],"tasks.":[20],"These":[21],"LLMs":[22],"demand":[23,83],"huge":[24],"computational":[25,166,173],"capabilities,":[26],"requiring":[27],"billions":[28],"of":[29,34,121],"parameters":[30],"and":[31,45,82,131,144,165],"enormous":[32],"amounts":[33],"labeled":[35],"data,":[36],"which":[37],"can":[38],"make":[39],"them":[40],"expensive":[41],"to":[42,63,154],"use,":[43],"optimize,":[44],"deploy":[46],"in":[47,171],"practice.":[48],"However,":[49],"studies":[51],"compressor-based":[53],"distance":[54],"metrics":[55],"have":[59],"been":[60],"proposed,":[61],"aiming":[62],"achieve":[64,155],"competitive":[65],"accuracy":[66],"when":[67],"compared":[68,112],"with":[69,113],"these":[70],"LLM":[71],"models.":[72],"Compression-based":[73],"are":[75],"usually":[76],"based":[77],"k-nearest":[79],"neighbors":[80],"(KNN)":[81],"very":[84],"few":[85],"parameters.":[87],"this":[89],"paper,":[90],"we":[91],"propose":[92],"a":[93,98],"compression-based":[94],"method":[95,118,151],"that":[96],"uses":[97],"Burkhard-Keller":[99],"tree":[100],"(BKTree)":[101],"similarity":[103],"search,":[104],"accelerating":[105],"KNN":[107],"compressed":[109],"data.":[110],"When":[111],"state-of-the-art,":[115],"proposed":[117,150],"achieved":[119],"speedups":[120],"20x,":[122],"25x,":[123],"7x,":[124],"6.6x,":[125],"8x,":[126],"10x,":[127],"1.4x,":[128],"1.9x,":[129],"11x,":[130],"12x":[132],"Brotli,":[135],"FSST,":[136],"LZ4,":[137],"LZAV,":[138],"LZF,":[139],"QuickLZ,":[140],"Shoco,":[141],"Smaz,":[142],"Snappy,":[143],"ZLib":[145],"compression":[146],"algorithms,":[147],"respectively.":[148],"The":[149],"is":[152],"able":[153],"similar":[156],"prediction":[157],"performance":[158],"results":[159],"while":[160],"reducing":[161],"average":[163],"runtime":[164],"resources,":[167],"demonstrating":[168],"its":[169],"advantage":[170],"saving":[172],"resources.":[174]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-12-03T00:00:00"}