{"id":"https://openalex.org/W7162492431","doi":"https://doi.org/10.1038/s41598-026-52560-1","title":"PSCSE: prompt-based contrastive learning with sample filtering for unsupervised sentence embedding","display_name":"PSCSE: prompt-based contrastive learning with sample filtering for unsupervised sentence embedding","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7162492431","doi":"https://doi.org/10.1038/s41598-026-52560-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/42204193"},"language":"en","primary_location":{"id":"doi:10.1038/s41598-026-52560-1","doi":"https://doi.org/10.1038/s41598-026-52560-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-52560-1","pdf_url":"https://www.nature.com/articles/s41598-026-52560-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41598-026-52560-1_reference.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137155278","display_name":"Biao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Li","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Science and Technology, Peace Street, Taiyuan, 030024, Shanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Science and Technology, Peace Street, Taiyuan, 030024, Shanxi, China","institution_ids":["https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137128524","display_name":"Xuebing Yang","orcid":"https://orcid.org/0000-0001-8343-125X","observed_orcids":["https://orcid.org/0000-0001-8343-125X"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebing Yang","raw_affiliation_strings":["Artificial Intelligence and Machine Learning Research Team, Institute of Automation, Chinese Academy of Sciences, Zhongguancun Street, Beijing, 100080, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Machine Learning Research Team, Institute of Automation, Chinese Academy of Sciences, Zhongguancun Street, Beijing, 100080, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010039524","display_name":"Liping Xie","orcid":"https://orcid.org/0000-0002-0986-9760","observed_orcids":["https://orcid.org/0000-0002-0986-9760"]},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"LiPing Xie","raw_affiliation_strings":["College of Computer Science and Technology, Taiyuan University of Science and Technology, Peace Street, Taiyuan, 030024, Shanxi, China. lib623@foxmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Taiyuan University of Science and Technology, Peace Street, Taiyuan, 030024, Shanxi, China. lib623@foxmail.com","institution_ids":["https://openalex.org/I46305995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010039524"],"corresponding_institution_ids":["https://openalex.org/I46305995"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37795743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0006000000284984708,"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":0.00039999998989515007,"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/contrastive-learning","display_name":"contrastive learning","score":0.984000027179718},{"id":"https://openalex.org/keywords/hard-negative-mining","display_name":"hard negative mining","score":0.5870000123977661},{"id":"https://openalex.org/keywords/semantic-textual-similarity","display_name":"semantic textual similarity","score":0.7590000033378601},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.609000027179718},{"id":"https://openalex.org/keywords/false-negative-results","display_name":"false-negative results","score":0.39800000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7287999987602234},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6499999761581421},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.487199991941452},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46149998903274536},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4390000104904175},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3095000088214874},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s41598-026-52560-1","doi":"https://doi.org/10.1038/s41598-026-52560-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-52560-1","pdf_url":"https://www.nature.com/articles/s41598-026-52560-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},{"id":"pmid:42204193","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42204193","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific reports","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13439071","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13439071/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13439071/pdf/41598_2026_Article_52560.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sci Rep","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:52d6b803933f46e29899bc6fb1279c9b","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/52d6b803933f46e29899bc6fb1279c9b","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Reports, Vol 16, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1038/s41598-026-52560-1","doi":"https://doi.org/10.1038/s41598-026-52560-1","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41598-026-52560-1","pdf_url":"https://www.nature.com/articles/s41598-026-52560-1_reference.pdf","source":{"id":"https://openalex.org/S196734849","display_name":"Scientific Reports","issn_l":"2045-2322","issn":["2045-2322"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1"],"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Reports","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7983814477920532,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2852496388","display_name":null,"funder_award_id":"62006139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5914912638","display_name":null,"funder_award_id":"62173328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6318245190","display_name":null,"funder_award_id":"2019YFB2103100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7977415929","display_name":null,"funder_award_id":"62006139","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7162492431.pdf","grobid_xml":"https://content.openalex.org/works/W7162492431.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"sentence":[1,98],"representation":[2],"learning":[3,12,92],"is":[4],"critical":[5],"in":[6,69,176],"natural":[7],"language":[8],"processing.":[9],"Recently,":[10],"contrastive":[11,91],"methods":[13,29,50,166],"achieved":[14,159],"remarkable":[15,160],"performance":[16,161],"by":[17,112,162,171],"optimizing":[18],"the":[19,27,33,37,42,46,53,59,62,77,102,107,113,126,129,136,140,146,153,164,177],"alignment":[20],"and":[21,72,158,169],"uniformity":[22,127],"of":[23,61,128],"embedding":[24,99],"spaces.":[25],"Nevertheless,":[26],"dominant":[28,165],"mainly":[30],"focus":[31],"on":[32,52,152],"data":[34],"augmentation":[35],"for":[36,45,58,76,96,139],"positive":[38],"samples":[39],"but":[40],"ignore":[41],"sampling":[43,56,74],"approach":[44,57,66,143],"negative":[47,63],"samples.":[48,64],"Most":[49],"rely":[51],"random":[54],"in-batch":[55],"generation":[60],"This":[65],"could":[67],"result":[68],"false":[70,147],"negatives":[71,110],"create":[73],"biases":[75],"model's":[78],"discriminative":[79],"ability.":[80],"To":[81],"address":[82,145],"this":[83],"problem,":[84],"we":[85,105,134],"propose":[86],"a":[87],"new":[88],"method":[89],"prompt-based":[90],"with":[93],"sample":[94,141],"filtering":[95,142],"unsupervised":[97],"(PSCSE).":[100],"In":[101,132],"proposed":[103],"model,":[104],"used":[106,135],"synthesized":[108],"hard":[109],"generated":[111],"\"NOT\"-style":[114],"prompts":[115],"(e.g.,":[116],"\"This":[117],"sentence:":[118],"[X]":[119],"does":[120],"not":[121],"mean":[122],"[MASK]\")":[123],"to":[124,144,173],"optimize":[125],"learned":[130],"representations.":[131],"addition,":[133],"auxiliary":[137],"encoder":[138],"negatives.":[148],"We":[149],"conducted":[150],"experiments":[151],"semantic":[154],"textual":[155],"similarity":[156],"dataset":[157],"surpassing":[163],"SimCSE,":[167],"E-SimCSE,":[168],"PromptBERT":[170],"up":[172],"1.0":[174],"points":[175],"average":[178],"Spearman's":[179],"correlation":[180],"score.":[181]},"counts_by_year":[],"updated_date":"2026-09-04T10:56:28.161419","created_date":"2026-05-28T00:00:00"}