{"id":"https://openalex.org/W7155404193","doi":"https://doi.org/10.3390/computers15050268","title":"Learning Scientific Document Representations via Triple-Source Automatic Supervision Without Annotations or Citations","display_name":"Learning Scientific Document Representations via Triple-Source Automatic Supervision Without Annotations or Citations","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155404193","doi":"https://doi.org/10.3390/computers15050268"},"language":"en","primary_location":{"id":"doi:10.3390/computers15050268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050268","pdf_url":"https://www.mdpi.com/2073-431X/15/5/268/pdf?version=1776945012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/15/5/268/pdf?version=1776945012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046228742","display_name":"Mussa Turdalyuly","orcid":"https://orcid.org/0000-0002-1470-3706"},"institutions":[{"id":"https://openalex.org/I105208703","display_name":"Almaty Management University","ror":"https://ror.org/00rhgqg04","country_code":"KZ","type":"education","lineage":["https://openalex.org/I105208703"]},{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]},{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Mussa Turdalyuly","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-1470-3706","affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]},{"raw_affiliation_string":"School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan","institution_ids":["https://openalex.org/I105208703","https://openalex.org/I4210143508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106348854","display_name":"\u0410\u0439\u043d\u04b1\u0440 \u0422\u04b1\u0440\u0441\u044b\u043d\u0445\u0430\u043d","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ainur Tursynkhan","raw_affiliation_strings":["Department of Computer and Information Technology, Purdue University, West Lafayette, IN 47907, USA","Software Engineering Department, International Engineering and Technological University, Almaty 050060, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0003-1332-3936","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Software Engineering Department, International Engineering and Technological University, Almaty 050060, Kazakhstan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017370698","display_name":"Aigerim Yerimbetova","orcid":"https://orcid.org/0000-0002-2013-1513"},"institutions":[{"id":"https://openalex.org/I105208703","display_name":"Almaty Management University","ror":"https://ror.org/00rhgqg04","country_code":"KZ","type":"education","lineage":["https://openalex.org/I105208703"]},{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]},{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aigerim Yerimbetova","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-2013-1513","affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]},{"raw_affiliation_string":"School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan","institution_ids":["https://openalex.org/I105208703","https://openalex.org/I4210143508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027718744","display_name":"Tolganay Turdalykyzy","orcid":"https://orcid.org/0000-0002-7720-7945"},"institutions":[{"id":"https://openalex.org/I105208703","display_name":"Almaty Management University","ror":"https://ror.org/00rhgqg04","country_code":"KZ","type":"education","lineage":["https://openalex.org/I105208703"]},{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]},{"id":"https://openalex.org/I4210143508","display_name":"International Information Technologies University","ror":"https://ror.org/042dtza69","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4210143508"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Tolganay Turdalykyzy","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]},{"raw_affiliation_string":"School of Engineering and Information Technology, META University, Almaty 050000, Kazakhstan","institution_ids":["https://openalex.org/I105208703","https://openalex.org/I4210143508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046791061","display_name":"Bakzhan Sakenov","orcid":"https://orcid.org/0000-0002-9849-6176"},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Bakzhan Sakenov","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-9849-6176","affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025484606","display_name":"\u041d\u0443\u0440\u0436\u0430\u043d \u041c\u0443\u043a\u0430\u0436\u0430\u043d\u043e\u0432","orcid":"https://orcid.org/0000-0003-4835-5751"},"institutions":[{"id":"https://openalex.org/I3130577743","display_name":"Narxoz University","ror":"https://ror.org/0523w7v09","country_code":"KZ","type":"education","lineage":["https://openalex.org/I3130577743"]},{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Nurzhan Mukazhanov","raw_affiliation_strings":["Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","School of Digital Technologies, Narxoz University, Almaty 050035, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0003-4835-5751","affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan","institution_ids":["https://openalex.org/I4210135055"]},{"raw_affiliation_string":"School of Digital Technologies, Narxoz University, Almaty 050035, Kazakhstan","institution_ids":["https://openalex.org/I3130577743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014865033","display_name":"Nazerke Baisholan","orcid":"https://orcid.org/0000-0002-8134-0466"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nazerke Baisholan","raw_affiliation_strings":["Department of Computer and Information Technology, Purdue University, West Lafayette, IN 47907, USA","Software Engineering Department, International Engineering and Technological University, Almaty 050060, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-8134-0466","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology, Purdue University, West Lafayette, IN 47907, USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Software Engineering Department, International Engineering and Technological University, Almaty 050060, Kazakhstan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027718744","https://openalex.org/A5046228742","https://openalex.org/A5046791061","https://openalex.org/A5106348854"],"corresponding_institution_ids":["https://openalex.org/I105208703","https://openalex.org/I219193219","https://openalex.org/I4210135055","https://openalex.org/I4210143508"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50117934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"5","first_page":"268","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.382999986410141,"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":0.382999986410141,"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":0.27480000257492065,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.07660000026226044,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.45579999685287476},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4453999996185303},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4185999929904938},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4138000011444092},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.397599995136261},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.37610000371932983},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.364300012588501},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6230999827384949},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4352000057697296},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4185999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4138000011444092},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.2639999985694885},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2778816267","wikidata":"https://www.wikidata.org/wiki/Q21015578","display_name":"Semantic query","level":4,"score":0.25459998846054077},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers15050268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050268","pdf_url":"https://www.mdpi.com/2073-431X/15/5/268/pdf?version=1776945012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d98b6d4d4ece48f9a19dc13a17740bb7","is_oa":true,"landing_page_url":"https://doaj.org/article/d98b6d4d4ece48f9a19dc13a17740bb7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 15, Iss 5, p 268 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers15050268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers15050268","pdf_url":"https://www.mdpi.com/2073-431X/15/5/268/pdf?version=1776945012","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5528573393821716,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314997","display_name":"Strong","ror":"https://ror.org/041vyzr56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7155404193.pdf","grobid_xml":"https://content.openalex.org/works/W7155404193.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"meaningful":[1],"representations":[2],"of":[3,63,115,145],"scientific":[4,56,146],"documents":[5,117],"is":[6],"essential":[7],"for":[8,51,127],"information":[9],"retrieval,":[10],"knowledge":[11],"discovery,":[12],"and":[13,25,69,99,130,134],"recommendation":[14],"systems.":[15],"Traditional":[16],"methods":[17],"such":[18],"as":[19],"TF-IDF":[20,133],"rely":[21,88],"on":[22,37,79,89,108],"lexical":[23],"matching":[24],"fail":[26],"to":[27],"capture":[28],"deeper":[29],"semantic":[30,71,120,151],"relationships,":[31],"while":[32],"transformer-based":[33],"approaches":[34,86],"typically":[35],"depend":[36],"limited":[38],"supervision":[39,49],"signals.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"propose":[45],"a":[46,73,80,109],"Triple-Source":[47],"automatic":[48],"framework":[50,77],"learning":[52,76,102],"document":[53,67],"embeddings":[54,140],"from":[55],"corpora.":[57],"The":[58,138],"model":[59],"integrates":[60],"three":[61],"types":[62],"supervision\u2013title\u2013abstract":[64],"pairs,":[65,68],"same-category":[66,128],"document-level":[70],"relationships\u2014within":[72],"unified":[74],"contrastive":[75],"based":[78],"multilingual":[81],"XLM-RoBERTa":[82],"encoder.":[83],"Unlike":[84],"prior":[85],"that":[87],"citation":[90],"graphs":[91],"or":[92],"manual":[93],"annotations,":[94],"our":[95],"method":[96],"enables":[97],"citation-free":[98],"annotation-free":[100],"representation":[101],"using":[103],"only":[104],"lightweight":[105],"metadata.":[106],"Experiments":[107],"publicly":[110],"available":[111],"arXiv":[112],"dataset":[113],"consisting":[114],"98,649":[116],"demonstrate":[118],"improved":[119,143],"retrieval":[121,129],"performance,":[122],"achieving":[123],"Recall@1":[124],"=":[125],"0.6181":[126],"outperforming":[131],"both":[132],"single-source":[135],"transformer":[136],"baselines.":[137],"learned":[139],"also":[141],"exhibit":[142],"clustering":[144],"domains,":[147],"indicating":[148],"more":[149],"structured":[150],"representations.":[152]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-24T00:00:00"}
