{"id":"https://openalex.org/W7133757004","doi":"https://doi.org/10.3390/make8030063","title":"Soft-Prompted Semantic Normalization for Unsupervised Analysis of the Scientific Literature","display_name":"Soft-Prompted Semantic Normalization for Unsupervised Analysis of the Scientific Literature","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7133757004","doi":"https://doi.org/10.3390/make8030063"},"language":"en","primary_location":{"id":"doi:10.3390/make8030063","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8030063","pdf_url":"https://www.mdpi.com/2504-4990/8/3/63/pdf?version=1772699961","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/8/3/63/pdf?version=1772699961","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123422819","display_name":"Ivan Malashin","orcid":null},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Ivan Malashin","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0008-8986-402X","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113237980","display_name":"Dmitry Martysyuk","orcid":null},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Martysyuk","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-1563-4036","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123391626","display_name":"Vadim Tynchenko","orcid":null},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vadim Tynchenko","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-3959-2969","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059986632","display_name":"Andrei Gantimurov","orcid":"https://orcid.org/0009-0001-4246-9742"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrei Gantimurov","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035410720","display_name":"V. A. Nelyub","orcid":null},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Nelyub","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0003-4263-2367","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111564097","display_name":"\u0410. \u0410. \u0411\u043e\u0440\u043e\u0434\u0443\u043b\u0438\u043d","orcid":null},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksei Borodulin","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0002-9648-2395","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5123391626","https://openalex.org/A5123422819"],"corresponding_institution_ids":["https://openalex.org/I177537411"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19409222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"3","first_page":"63","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.29919999837875366,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.29919999837875366,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1339000016450882,"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":0.053199999034404755,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6312000155448914},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.560699999332428},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5450999736785889},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5085999965667725},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.4618000090122223},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.44749999046325684},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.43209999799728394},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.39879998564720154},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268999814987183},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.656000018119812},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788000226020813},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.44749999046325684},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.43209999799728394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make8030063","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8030063","pdf_url":"https://www.mdpi.com/2504-4990/8/3/63/pdf?version=1772699961","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d5317a35bce14d7db3e7b6f00a478111","is_oa":true,"landing_page_url":"https://doaj.org/article/d5317a35bce14d7db3e7b6f00a478111","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":"Machine Learning and Knowledge Extraction, Vol 8, Iss 3, p 63 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make8030063","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8030063","pdf_url":"https://www.mdpi.com/2504-4990/8/3/63/pdf?version=1772699961","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5641846656799316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133757004.pdf","grobid_xml":"https://content.openalex.org/works/W7133757004.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1499692130","https://openalex.org/W2040313973","https://openalex.org/W2072373399","https://openalex.org/W2072661909","https://openalex.org/W2126105956","https://openalex.org/W2341844252","https://openalex.org/W2558405088","https://openalex.org/W2732547613","https://openalex.org/W2770641296","https://openalex.org/W2970641574","https://openalex.org/W3027173706","https://openalex.org/W3110435694","https://openalex.org/W3174836143","https://openalex.org/W4206529673","https://openalex.org/W4210853506","https://openalex.org/W4214726584","https://openalex.org/W4280637601","https://openalex.org/W4293023648","https://openalex.org/W4312055677","https://openalex.org/W4383215352","https://openalex.org/W4385570594","https://openalex.org/W4390098213","https://openalex.org/W4391591760","https://openalex.org/W4391697001","https://openalex.org/W4393089671","https://openalex.org/W4396843692","https://openalex.org/W4399492476","https://openalex.org/W4399665748","https://openalex.org/W4400984542","https://openalex.org/W4401043119","https://openalex.org/W4401671778","https://openalex.org/W4402117799","https://openalex.org/W4402987946","https://openalex.org/W4403510631","https://openalex.org/W4404599568","https://openalex.org/W4404783118","https://openalex.org/W4405184257","https://openalex.org/W4405674754","https://openalex.org/W4406354447","https://openalex.org/W4406415973","https://openalex.org/W4407236106","https://openalex.org/W4407571719","https://openalex.org/W4408225310","https://openalex.org/W4408785507","https://openalex.org/W4409098775","https://openalex.org/W4409545474","https://openalex.org/W4410853633","https://openalex.org/W4411063470","https://openalex.org/W4411120389","https://openalex.org/W4412567252","https://openalex.org/W4412748114","https://openalex.org/W4414156393","https://openalex.org/W4414724404","https://openalex.org/W4415986011","https://openalex.org/W4416402297","https://openalex.org/W4417123188","https://openalex.org/W7124831230"],"related_works":[],"abstract_inverted_index":{"Mapping":[0],"thematic":[1,137],"structure":[2],"in":[3],"large":[4,25,140],"scientific":[5],"corpora":[6],"enables":[7],"the":[8,75,93,105],"systematic":[9],"analysis":[10,128],"of":[11,77,92],"research":[12,71],"trends":[13],"and":[14,99,115,132],"conceptual":[15,55],"organization.":[16],"This":[17],"work":[18],"presents":[19],"an":[20],"unsupervised":[21,136],"framework":[22,40],"that":[23,48,104,121],"leverages":[24],"language":[26],"models":[27],"(LLMs)":[28],"as":[29],"fixed":[30],"semantic":[31,46,85,123],"inference":[32],"operators":[33],"guided":[34],"by":[35],"structured":[36],"soft":[37],"prompts.":[38],"The":[39,118],"transforms":[41],"raw":[42],"abstracts":[43,102],"into":[44,61],"normalized":[45],"representations":[47,58],"reduce":[49],"stylistic":[50],"variability":[51],"while":[52],"retaining":[53],"core":[54],"content.":[56],"These":[57],"are":[59],"embedded":[60],"a":[62,130],"continuous":[63],"vector":[64],"space,":[65],"where":[66],"density-based":[67],"clustering":[68],"identifies":[69],"latent":[70],"themes":[72],"without":[73],"predefining":[74],"number":[76],"topics.":[78],"Cluster-level":[79],"interpretation":[80],"is":[81],"performed":[82],"using":[83],"LLM-based":[84],"decoding":[86],"to":[87],"generate":[88],"concise,":[89],"human-readable":[90],"descriptions":[91],"discovered":[94],"themes.":[95],"Experiments":[96],"on":[97],"ICML":[98],"ACL":[100],"2025":[101],"demonstrate":[103],"method":[106],"produces":[107],"coherent":[108],"clusters":[109],"reflecting":[110],"problem":[111],"formulations,":[112],"methodological":[113],"contributions,":[114],"empirical":[116],"contexts.":[117],"findings":[119],"indicate":[120],"prompt-driven":[122],"normalization":[124],"combined":[125],"with":[126],"geometric":[127],"provides":[129],"scalable":[131],"model-agnostic":[133],"approach":[134],"for":[135],"discovery":[138],"across":[139],"scholarly":[141],"corpora.":[142]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-06T00:00:00"}