{"id":"https://openalex.org/W6992952617","doi":null,"title":"Modelos de embeddings de senten\u00e7as usando matryoshka representation learning","display_name":"Modelos de embeddings de senten\u00e7as usando matryoshka representation learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6992952617"},"language":"en","primary_location":{"id":"pmh:oai:www.lume.ufrgs.br:10183/294936","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10183/294936","pdf_url":"https://lume.ufrgs.br/bitstream/10183/294936/1/001290953.pdf","source":{"id":"https://openalex.org/S4306401468","display_name":"Lume (Universidade Federal do Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210097146","host_organization_name":"Hospital de Cl\u00ednicas de Porto Alegre","host_organization_lineage":["https://openalex.org/I4210097146"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Trabalho de conclus\u00e3o de gradua\u00e7\u00e3o"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lume.ufrgs.br/bitstream/10183/294936/1/001290953.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pinto, Gabriel Vogel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pinto, Gabriel Vogel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.9990000128746033,"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":9.999999747378752e-05,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/sentence-embeddings","display_name":"sentence embeddings","score":0.9980000257492065},{"id":"https://openalex.org/keywords/sentence-bert","display_name":"Sentence-BERT","score":0.9150000214576721},{"id":"https://openalex.org/keywords/portuguese-language","display_name":"Portuguese language","score":0.9300000071525574},{"id":"https://openalex.org/keywords/multilingual-word-embeddings","display_name":"multilingual embeddings","score":0.6790000200271606},{"id":"https://openalex.org/keywords/semantic-textual-similarity","display_name":"semantic textual similarity","score":0.7850000262260437},{"id":"https://openalex.org/keywords/low-dimensional-embedding","display_name":"low-dimensional embedding","score":0.7200000286102295},{"id":"https://openalex.org/keywords/memory-efficiency","display_name":"memory efficiency","score":0.6790000200271606},{"id":"https://openalex.org/keywords/underrepresented-languages","display_name":"underrepresented languages","score":0.6850000023841858},{"id":"https://openalex.org/keywords/bfloat16","display_name":"bfloat16","score":0.7879999876022339}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7166000008583069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6814000010490417},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6207000017166138},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5486000180244446},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5081999897956848},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4666999876499176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.4047999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.lume.ufrgs.br:10183/294936","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10183/294936","pdf_url":"https://lume.ufrgs.br/bitstream/10183/294936/1/001290953.pdf","source":{"id":"https://openalex.org/S4306401468","display_name":"Lume (Universidade Federal do Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210097146","host_organization_name":"Hospital de Cl\u00ednicas de Porto Alegre","host_organization_lineage":["https://openalex.org/I4210097146"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Trabalho de conclus\u00e3o de gradua\u00e7\u00e3o"}],"best_oa_location":{"id":"pmh:oai:www.lume.ufrgs.br:10183/294936","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10183/294936","pdf_url":"https://lume.ufrgs.br/bitstream/10183/294936/1/001290953.pdf","source":{"id":"https://openalex.org/S4306401468","display_name":"Lume (Universidade Federal do Rio Grande do Sul)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210097146","host_organization_name":"Hospital de Cl\u00ednicas de Porto Alegre","host_organization_lineage":["https://openalex.org/I4210097146"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Trabalho de conclus\u00e3o de gradua\u00e7\u00e3o"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6992952617.pdf","grobid_xml":"https://content.openalex.org/works/W6992952617.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1555148682","https://openalex.org/W1614298861","https://openalex.org/W2064675550","https://openalex.org/W2133564696","https://openalex.org/W2170240176","https://openalex.org/W2493916176","https://openalex.org/W2611029872","https://openalex.org/W2786672974","https://openalex.org/W2787560479","https://openalex.org/W2953084091","https://openalex.org/W2965373594","https://openalex.org/W2980282514","https://openalex.org/W2981852735","https://openalex.org/W3030163527","https://openalex.org/W3041133507","https://openalex.org/W3048379775","https://openalex.org/W3093334098","https://openalex.org/W3096266342","https://openalex.org/W3156636935","https://openalex.org/W3198713493","https://openalex.org/W4246183800","https://openalex.org/W4308067211","https://openalex.org/W4386576685","https://openalex.org/W4391709827","https://openalex.org/W4392223206","https://openalex.org/W4396913165","https://openalex.org/W4402671936","https://openalex.org/W4402856368","https://openalex.org/W4404356592","https://openalex.org/W4413414331","https://openalex.org/W4416037315","https://openalex.org/W6969259846","https://openalex.org/W7133214597"],"related_works":["https://openalex.org/W7167639964","https://openalex.org/W4382866648","https://openalex.org/W3217326652","https://openalex.org/W3135641865","https://openalex.org/W3039695075","https://openalex.org/W7120660652","https://openalex.org/W4392122227","https://openalex.org/W4387424400","https://openalex.org/W7167572859","https://openalex.org/W3096266342"],"abstract_inverted_index":{"Sentence":[0],"embeddings":[1,48],"are":[2,22],"a":[3,102],"core":[4],"part":[5],"of":[6,44,58,114],"many":[7,29],"modern":[8],"Natural":[9],"Language":[10],"Processing":[11],"ap":[12],"plications,":[13],"such":[14],"as":[15],"search":[16],"engines.":[17],"Their":[18],"multilingual":[19,179],"variants,":[20],"which":[21],"able":[23],"to":[24,39,92,222],"produce":[25],"vector":[26,94],"representations":[27,95],"for":[28,76,96],"languages,":[30],"exhibit":[31],"significantly":[32],"lower":[33,148],"performance":[34,113,172,190,211,224],"in":[35,56,157,173],"underrepresented":[36],"languages":[37],"compared":[38],"English.":[40],"Also,":[41],"the":[42,45,50,72,77,81,97,112,115,123,158,165,174,178,208],"dimensionality":[43,104,149],"pro":[46],"duced":[47],"and":[49,60,126,131,186,217],"model\u2019s":[51,210],"size":[52],"might":[53],"be":[54],"prohibitive":[55],"terms":[57],"memory":[59],"cost.":[61],"In":[62],"this":[63,136],"work,":[64],"we":[65,139,205],"develop":[66],"two":[67],"sentence":[68],"embedding":[69,195],"models":[70,117,143],"using":[71,164],"Sentence-BERT":[73],"(SBERT)":[74],"framework":[75],"Portuguese":[78,98,130,194],"language,":[79],"employing":[80],"Matryoshka":[82],"Represen":[83],"tation":[84],"Learning":[85],"(MRL)":[86],"loss":[87],"function.":[88],"The":[89],"goal":[90],"is":[91],"enhance":[93],"language":[99],"while":[100,197,226],"maintaining":[101],"reduced":[103],"with":[105,181,215,220],"no":[106,223],"computa":[107],"tional":[108],"overhead.":[109],"We":[110],"assess":[111],"proposed":[116,209],"against":[118,127,191],"their":[119,151],"variants":[120],"trained":[121,199],"without":[122],"MRL":[124],"approach":[125],"other":[128],"open-source":[129],"multi":[132],"lingual":[133],"models.":[134],"Through":[135],"evaluation":[137],"method,":[138],"found":[140],"that":[141],"MRL-based":[142],"(i)":[144],"perform":[145],"better":[146,171],"at":[147,182],"than":[150,177],"non-MRL":[152],"counterparts":[153],"by":[154],"0.01-0.02":[155],"points":[156],"Semantic":[159],"Textual":[160],"Similarity":[161],"(STS)":[162],"benchmark":[163,176],"Pearson":[166],"Correlation":[167],"metric;":[168],"(ii)":[169],"have":[170],"STS":[175],"models,":[180,196],"least":[183],"0.06":[184],"points;":[185],"(iii)":[187],"present":[188],"competitive":[189],"state-of-the":[192],"art":[193],"being":[198,213],"on":[200],"much":[201],"less":[202,229],"data.":[203],"Additionally,":[204],"also":[206],"evaluate":[207],"when":[212],"used":[214],"float32":[216],"bfloat16":[218],"representations,":[219],"little":[221],"variation":[225],"occupying":[227],"50%":[228],"memory.":[230]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}