{"id":"https://openalex.org/W4389520386","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.737","title":"SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives","display_name":"SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389520386","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.737"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.737","pdf_url":"https://aclanthology.org/2023.emnlp-main.737.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.emnlp-main.737.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101622577","display_name":"Jiahao Xu","orcid":"https://orcid.org/0000-0001-6776-8215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiahao Xu","raw_affiliation_strings":["Nanyang Technological University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078512276","display_name":"Wei Shao","orcid":"https://orcid.org/0000-0001-7531-1055"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Shao","raw_affiliation_strings":["City Univeristy of Hong Kong,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City Univeristy of Hong Kong,","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110979711","display_name":"Lihui Chen","orcid":"https://orcid.org/0009-0003-5231-5151"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lihui Chen","raw_affiliation_strings":["Nanyang Technological University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005411806","display_name":"Lemao Liu","orcid":"https://orcid.org/0000-0003-3804-5768"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lemao Liu","raw_affiliation_strings":["Tencent AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12028","last_page":"12040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7577493190765381},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.736059844493866},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.611910879611969},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5931780338287354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5817753672599792},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5326034426689148},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5311810970306396},{"id":"https://openalex.org/keywords/contrastive-analysis","display_name":"Contrastive analysis","score":0.506782591342926},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.46623656153678894},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4121001064777374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4090384542942047},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39167723059654236},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14618098735809326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14449700713157654},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10618692636489868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577493190765381},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.736059844493866},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.611910879611969},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5931780338287354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5817753672599792},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5326034426689148},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5311810970306396},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.506782591342926},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.46623656153678894},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4121001064777374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4090384542942047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39167723059654236},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14618098735809326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14449700713157654},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10618692636489868},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.737","pdf_url":"https://aclanthology.org/2023.emnlp-main.737.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/68e5d9bf-8945-4de5-a647-122b99c23cbf","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/68e5d9bf-8945-4de5-a647-122b99c23cbf","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xu, J, Shao, W, Chen, L & Liu, L 2023, SimCSE++ : Improving Contrastive Learning for Sentence Embeddings from Two Perspectives. in H Bouamor, J Pino & K Bali (eds), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. EMNLP - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics, pp. 12028-12040, 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), Singapore, 6/12/23. https://doi.org/10.18653/v1/2023.emnlp-main.737","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.737","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.737","pdf_url":"https://aclanthology.org/2023.emnlp-main.737.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4389520386.pdf"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1521968289","https://openalex.org/W1522301498","https://openalex.org/W1537220347","https://openalex.org/W1614298861","https://openalex.org/W1904365287","https://openalex.org/W2095705004","https://openalex.org/W2138204974","https://openalex.org/W2152790380","https://openalex.org/W2185175083","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2251861449","https://openalex.org/W2605035112","https://openalex.org/W2786464815","https://openalex.org/W2963341956","https://openalex.org/W2963804993","https://openalex.org/W2963918774","https://openalex.org/W2969985801","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W3099700870","https://openalex.org/W3100652389","https://openalex.org/W3102363610","https://openalex.org/W3104033643","https://openalex.org/W3105220303","https://openalex.org/W3105816068","https://openalex.org/W3115295967","https://openalex.org/W3118062200","https://openalex.org/W3122838366","https://openalex.org/W3134652006","https://openalex.org/W3154229486","https://openalex.org/W3156636935","https://openalex.org/W3173169192","https://openalex.org/W3173188814","https://openalex.org/W3173190788","https://openalex.org/W3173783447","https://openalex.org/W3175362188","https://openalex.org/W3176047188","https://openalex.org/W4221152557","https://openalex.org/W4224313754","https://openalex.org/W4224950137","https://openalex.org/W4225385501","https://openalex.org/W4249573750","https://openalex.org/W4283797513","https://openalex.org/W4285149128","https://openalex.org/W4285157416","https://openalex.org/W4285296644","https://openalex.org/W4286891192","https://openalex.org/W4287592659","https://openalex.org/W4287824654","https://openalex.org/W4385573552","https://openalex.org/W4389520067"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"This":[0],"paper":[1],"improves":[2],"contrastive":[3,67,85,129],"learning":[4,68,86,130],"for":[5,19,89,142],"sentence":[6,90],"embeddings":[7],"from":[8,29],"two":[9],"perspectives:":[10],"handling":[11],"dropout":[12,27],"noise":[13,28],"and":[14,63,79],"addressing":[15],"feature":[16,61],"corruption.":[17],"Specifically,":[18],"the":[20,26,33,54,112,122],"first":[21],"perspective,":[22],"we":[23,37,52],"identify":[24],"that":[25,98],"negative":[30],"pairs":[31],"affects":[32],"model's":[34],"performance.":[35],"Therefore,":[36],"propose":[38,64],"a":[39,65,105,135],"simple":[40],"yet":[41],"effective":[42],"method":[43,124],"to":[44,60,70,83,104,111,125],"deal":[45],"with":[46,117],"such":[47],"type":[48],"of":[49,57,107,137],"noise.":[50],"Secondly,":[51],"pinpoint":[53],"rank":[55],"bottleneck":[56],"current":[58],"solutions":[59],"corruption":[62],"dimension-wise":[66],"objective":[69],"address":[71],"this":[72],"issue.":[73],"Both":[74],"proposed":[75,101,123],"methods":[76,102],"are":[77],"generic":[78],"can":[80],"be":[81],"applied":[82],"any":[84],"based":[87,131],"models":[88],"embeddings.":[91],"Experimental":[92],"results":[93,133],"on":[94],"standard":[95],"benchmarks":[96],"demonstrate":[97],"combining":[99],"both":[100],"leads":[103],"gain":[106,136],"1.8":[108],"points":[109],"compared":[110],"strong":[113,128],"baseline":[114],"SimCSE":[115],"configured":[116],"BERT":[118],"base.":[119],"Furthermore,":[120],"applying":[121],"DiffCSE,":[126],"another":[127],"baseline,":[132],"in":[134],"1.4":[138],"points.":[139],"\u00a92023":[140],"Association":[141],"Computational":[143],"Linguistics.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}