{"id":"https://openalex.org/W4403582642","doi":"https://doi.org/10.1145/3627673.3679745","title":"Not All Negatives are Equally Negative: Soft Contrastive Learning for Unsupervised Sentence Representations","display_name":"Not All Negatives are Equally Negative: Soft Contrastive Learning for Unsupervised Sentence Representations","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582642","doi":"https://doi.org/10.1145/3627673.3679745"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679745","pdf_url":null,"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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679745","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102941830","display_name":"Haojie Zhuang","orcid":"https://orcid.org/0000-0003-4387-6347"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Haojie Zhuang","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070697660","display_name":"Wei Emma Zhang","orcid":"https://orcid.org/0000-0002-0406-5974"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Emma Zhang","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009644404","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0002-4408-1952"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065555672","display_name":"Weitong Chen","orcid":"https://orcid.org/0000-0003-1001-7925"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Weitong Chen","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080744092","display_name":"Quan Z. Sheng","orcid":"https://orcid.org/0000-0002-3326-4147"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102941830"],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.7724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77125083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3591","last_page":"3601"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9995999932289124,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.7027305364608765},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6450089812278748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5942150950431824},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.562821626663208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46999916434288025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37448886036872864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027305364608765},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6450089812278748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942150950431824},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.562821626663208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46999916434288025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37448886036872864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679745","pdf_url":null,"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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679745","pdf_url":null,"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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1516184288","https://openalex.org/W1583837637","https://openalex.org/W1593271688","https://openalex.org/W2066814510","https://openalex.org/W2114524997","https://openalex.org/W2126400076","https://openalex.org/W2133458109","https://openalex.org/W2160660844","https://openalex.org/W2163455955","https://openalex.org/W2250539671","https://openalex.org/W2462305634","https://openalex.org/W2595551253","https://openalex.org/W2605035112","https://openalex.org/W2625561335","https://openalex.org/W2739351760","https://openalex.org/W2740887992","https://openalex.org/W2891177506","https://openalex.org/W2963804993","https://openalex.org/W2970641574","https://openalex.org/W3104033643","https://openalex.org/W3105816068","https://openalex.org/W3156636935","https://openalex.org/W3175593095","https://openalex.org/W4224313754","https://openalex.org/W4225385501","https://openalex.org/W4285241989","https://openalex.org/W4285296644","https://openalex.org/W4312382935","https://openalex.org/W4385569706","https://openalex.org/W4385570119","https://openalex.org/W4385570895","https://openalex.org/W4385571485","https://openalex.org/W4386576685","https://openalex.org/W4389519126","https://openalex.org/W4389520386","https://openalex.org/W4389524150","https://openalex.org/W4389524421"],"related_works":["https://openalex.org/W2375873920","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2392760275","https://openalex.org/W2083530853","https://openalex.org/W2009831055","https://openalex.org/W2393172683","https://openalex.org/W3211744874","https://openalex.org/W1994626569","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,9],"has":[2],"been":[3],"extensively":[4],"studied":[5],"in":[6,14,39,115],"sentence":[7,21],"representation":[8],"as":[10,32,43,173,175],"it":[11],"demonstrates":[12],"effectiveness":[13],"various":[15],"downstream":[16],"applications,":[17],"where":[18,180],"the":[19,40,57,61,65,72,77,86,93,107,116,122,125,129,134,148,154],"same":[20,41],"with":[22,92,156],"different":[23,58],"dropout":[24],"masks":[25],"(or":[26],"other":[27,37,157],"augmentation":[28],"methods)":[29],"is":[30],"considered":[31],"positive":[33],"pair":[34,114],"while":[35],"taking":[36],"sentences":[38],"mini-batch":[42],"negative":[44,52,62,87,113,126],"pairs.":[45],"However,":[46],"these":[47],"methods":[48,139],"mostly":[49],"treat":[50],"all":[51],"examples":[53,63,88,127],"equally":[54],"and":[55,64,95,128,143,153,169,178],"overlook":[56],"similarities":[59,91,123],"between":[60],"anchors,":[66],"which":[67],"thus":[68,96],"fail":[69],"to":[70,121,140,187],"capture":[71],"fine-grained":[73],"semantic":[74,165],"information":[75],"of":[76,111,124,137],"sentences.":[78],"To":[79],"address":[80],"this":[81],"issue,":[82],"we":[83,160,181],"explicitly":[84],"differentiate":[85],"by":[89],"their":[90],"anchor,":[94],"propose":[97],"a":[98],"simple":[99],"yet":[100],"effective":[101],"method":[102],"SoftCSE":[103,145],"that":[104],"individualizes":[105],"either":[106],"weight":[108],"or":[109],"temperature":[110],"each":[112],"standard":[117],"InfoNCE":[118],"loss":[119],"according":[120],"anchors.":[130],"We":[131],"further":[132],"provide":[133],"theoretical":[135],"analysis":[136,152],"our":[138],"show":[141],"why":[142],"how":[144],"works,":[146],"including":[147],"optimal":[149],"solution,":[150],"gradient":[151],"connection":[155],"loss.":[158],"Empirically,":[159],"conduct":[161],"extensive":[162],"experiments":[163],"on":[164],"textual":[166],"similarity":[167],"(STS)":[168],"transfer":[170],"(TR)":[171],"tasks,":[172],"well":[174],"text":[176],"retrieval":[177],"reranking,":[179],"observe":[182],"significant":[183],"performance":[184],"improvements":[185],"compared":[186],"strong":[188],"baseline":[189],"models.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}