{"id":"https://openalex.org/W7117544131","doi":"https://doi.org/10.1109/iisa66859.2025.11311194","title":"Document Embeddings for Long Texts from Transformers and Autoencoders","display_name":"Document Embeddings for Long Texts from Transformers and Autoencoders","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W7117544131","doi":"https://doi.org/10.1109/iisa66859.2025.11311194"},"language":null,"primary_location":{"id":"doi:10.1109/iisa66859.2025.11311194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa66859.2025.11311194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information, Intelligence, Systems & Applications (IISA)","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/A5115452048","display_name":"Lenos Christou","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Lenos Christou","raw_affiliation_strings":["University of Patras,Computer Engineering and Informatics Department,Rion,Greece"],"raw_orcid":"https://orcid.org/0009-0009-1141-9556","affiliations":[{"raw_affiliation_string":"University of Patras,Computer Engineering and Informatics Department,Rion,Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061170947","display_name":"Agorakis Bompotas","orcid":"https://orcid.org/0000-0002-6063-8562"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Agorakis Bompotas","raw_affiliation_strings":["University of Patras,Computer Engineering and Informatics Department,Rion,Greece"],"raw_orcid":"https://orcid.org/0000-0002-6063-8562","affiliations":[{"raw_affiliation_string":"University of Patras,Computer Engineering and Informatics Department,Rion,Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082933732","display_name":"Nikitas-Rigas Kalogeropoulos","orcid":"https://orcid.org/0000-0002-0525-6924"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikitas - Rigas Kalogeropoulos","raw_affiliation_strings":["University of Patras,Computer Engineering and Informatics Department,Rion,Greece"],"raw_orcid":"https://orcid.org/0000-0002-0525-6924","affiliations":[{"raw_affiliation_string":"University of Patras,Computer Engineering and Informatics Department,Rion,Greece","institution_ids":["https://openalex.org/I174878644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087360505","display_name":"Christos Makris","orcid":"https://orcid.org/0000-0003-2571-7449"},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos Makris","raw_affiliation_strings":["University of Patras,Computer Engineering and Informatics Department,Rion,Greece"],"raw_orcid":"https://orcid.org/0000-0003-2571-7449","affiliations":[{"raw_affiliation_string":"University of Patras,Computer Engineering and Informatics Department,Rion,Greece","institution_ids":["https://openalex.org/I174878644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174878644"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7759223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.37869998812675476,"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":0.37869998812675476,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.17149999737739563,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.10199999809265137,"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/autoencoder","display_name":"Autoencoder","score":0.8179000020027161},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.661899983882904},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.652999997138977},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6205000281333923},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6050999760627747},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5393000245094299},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.48249998688697815}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8179000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733299970626831},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.661899983882904},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.652999997138977},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6205000281333923},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5059999823570251},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.48249998688697815},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iisa66859.2025.11311194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa66859.2025.11311194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information, Intelligence, Systems & Applications (IISA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W2064675550","https://openalex.org/W2084229232","https://openalex.org/W2101234009","https://openalex.org/W2122538988","https://openalex.org/W2889326414","https://openalex.org/W2970641574","https://openalex.org/W3080427797","https://openalex.org/W3145004415","https://openalex.org/W4239025696","https://openalex.org/W4385245566","https://openalex.org/W4391840390"],"related_works":[],"abstract_inverted_index":{"In":[0],"document":[1,20,100,140,203],"categorization,":[2],"the":[3,10,35,46,67,95,109,126,135,151,165,181,184,188,194,200,207],"escalating":[4],"volume":[5],"of":[6,37,167,180,196],"digital":[7],"data":[8],"underscores":[9,193],"critical":[11],"need":[12],"for":[13,23,40,74,88,97,115,175,209],"advanced":[14],"techniques":[15],"in":[16,130,139,177,198,202],"generating":[17],"semantically":[18],"rich":[19],"embedding,":[21,42],"particularly":[22],"topic":[24],"modelling":[25],"applications.":[26],"This":[27,105,133,191],"article":[28,192],"presents":[29],"a":[30,78],"novel":[31],"methodology":[32],"that":[33,62],"leverages":[34],"capabilities":[36],"SentenceBERT":[38],"(SBERT)":[39],"sentence":[41,86],"aiming":[43],"to":[44,83],"address":[45],"challenges":[47],"associated":[48],"with":[49],"embedding":[50,73,141,204],"longer":[51],"texts.":[52],"The":[53,119,170],"process":[54,186],"begins":[55],"by":[56],"decomposing":[57],"documents":[58],"into":[59],"individual":[60],"sentences":[61],"can":[63],"be":[64],"processed":[65],"using":[66],"SBERT":[68],"model":[69],"which":[70],"generates":[71],"an":[72,103],"each":[75,89],"sentence.":[76],"Subsequently,":[77],"clustering":[79,185],"algorithm":[80],"is":[81,147],"employed":[82],"select":[84],"representative":[85],"embeddings":[87,92,101],"document.":[90],"These":[91],"serve":[93],"as":[94],"foundation":[96],"constructing":[98],"comprehensive":[99],"through":[102],"autoencoder.":[104],"research":[106],"exclusively":[107],"explores":[108],"autoencoder":[110,120],"approach,":[111],"discarding":[112],"alternative":[113],"methods":[114],"brevity":[116],"and":[117,187,212],"focus.":[118],"strategy":[121],"showed":[122],"promising":[123],"results,":[124],"outperforming":[125],"base":[127],"model,":[128],"SBERT,":[129],"every":[131],"scenario.":[132],"highlights":[134],"method's":[136],"potential":[137,195],"effectiveness":[138],"tasks":[142],"where":[143],"understanding":[144],"long":[145],"context":[146],"important.":[148],"Moreover,":[149],"when":[150],"Transformer":[152],"Autoencoder":[153],"was":[154],"fine-tuned":[155],"on":[156],"test":[157],"data,":[158],"it":[159],"achieved":[160],"even":[161],"grater":[162],"performance,":[163],"underscoring":[164],"viability":[166],"this":[168],"approach.":[169],"findings":[171],"suggest":[172],"considerable":[173],"room":[174],"improvement":[176],"various":[178],"aspects":[179],"methodology,":[182],"including":[183],"encoder":[189],"architecture.":[190],"autoencoders":[197],"advancing":[199],"state-of-the-art":[201],"technologies,":[205],"setting":[206],"stage":[208],"further":[210],"refinement":[211],"exploration.":[213]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-12-30T00:00:00"}