{"id":"https://openalex.org/W4386794616","doi":"https://doi.org/10.1145/3583780.3614833","title":"DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective","display_name":"DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4386794616","doi":"https://doi.org/10.1145/3583780.3614833"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3614833","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.07396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059044562","display_name":"Pu Miao","orcid":"https://orcid.org/0000-0002-9308-5247"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pu Miao","raw_affiliation_strings":["Sina Weibo, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sina Weibo, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031006150","display_name":"Zeyao Du","orcid":"https://orcid.org/0000-0002-9054-3337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyao Du","raw_affiliation_strings":["China Literature Limited, Shang Hai, China"],"affiliations":[{"raw_affiliation_string":"China Literature Limited, Shang Hai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055280414","display_name":"J.Y Zhang","orcid":"https://orcid.org/0000-0002-7982-3194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlin Zhang","raw_affiliation_strings":["Sina Weibo, BeiJing, China"],"affiliations":[{"raw_affiliation_string":"Sina Weibo, BeiJing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059044562"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0548,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81683065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1847","last_page":"1856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.9911999702453613,"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":0.7395517826080322},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7030667066574097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6827978491783142},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6558489203453064},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5806121230125427},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.5791877508163452},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4652481973171234},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4558982849121094},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.43917179107666016},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08299675583839417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395517826080322},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7030667066574097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6827978491783142},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6558489203453064},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5806121230125427},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.5791877508163452},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4652481973171234},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4558982849121094},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.43917179107666016},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08299675583839417},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3583780.3614833","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3614833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.07396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07396","pdf_url":"https://arxiv.org/pdf/2309.07396","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.07396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.07396","pdf_url":"https://arxiv.org/pdf/2309.07396","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386794616.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2102443632","https://openalex.org/W2126400076","https://openalex.org/W2133458109","https://openalex.org/W2152180407","https://openalex.org/W2250539671","https://openalex.org/W2250790822","https://openalex.org/W2251861449","https://openalex.org/W2340526403","https://openalex.org/W2462305634","https://openalex.org/W2507134384","https://openalex.org/W2771976988","https://openalex.org/W2790235966","https://openalex.org/W2797400361","https://openalex.org/W2878188201","https://openalex.org/W2896457183","https://openalex.org/W2950268498","https://openalex.org/W2965373594","https://openalex.org/W2966610483","https://openalex.org/W2970597249","https://openalex.org/W2970641574","https://openalex.org/W2979826702","https://openalex.org/W3035060554","https://openalex.org/W3102363610","https://openalex.org/W3105712174","https://openalex.org/W3105816068","https://openalex.org/W3118062200","https://openalex.org/W3154229486","https://openalex.org/W3156636935","https://openalex.org/W3171007011","https://openalex.org/W3175362188","https://openalex.org/W3196790170","https://openalex.org/W4224313754","https://openalex.org/W4225385501","https://openalex.org/W4238846128","https://openalex.org/W4281743053","https://openalex.org/W4285296644","https://openalex.org/W4287592659","https://openalex.org/W4294170691","https://openalex.org/W4298443704","https://openalex.org/W4313908941","https://openalex.org/W4385392860","https://openalex.org/W4385573170"],"related_works":["https://openalex.org/W4362554880","https://openalex.org/W4281684980","https://openalex.org/W4386875279","https://openalex.org/W2171721708","https://openalex.org/W4390963114","https://openalex.org/W3214527415","https://openalex.org/W4287887864","https://openalex.org/W1495104519","https://openalex.org/W4225584739","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Several":[0],"prior":[1],"studies":[2],"have":[3,27],"suggested":[4],"that":[5,63,90,197],"word":[6],"frequency":[7],"biases":[8,52,97,109,163],"can":[9,157],"cause":[10],"the":[11,38,77,93,123,133,159,181,201],"Bert":[12],"model":[13],"to":[14,36,67,131,171,179],"learn":[15,68],"indistinguishable":[16],"sentence":[17,34,55,81,103,128,152],"embeddings.":[18,104],"Contrastive":[19],"learning":[20,83,101,121,127,141],"schemes":[21],"such":[22,53],"as":[23,54],"SimCSE":[24],"and":[25,58,88,122,175,183],"ConSERT":[26],"already":[28],"been":[29],"adopted":[30],"successfully":[31],"in":[32,119,138,142],"unsupervised":[33,143],"embedding":[35,82,129],"improve":[37],"quality":[39],"of":[40,79,95,135,161,211],"embeddings":[41],"by":[42,112,164],"reducing":[43],"this":[44,73],"bias.":[45],"However,":[46],"these":[47,162],"methods":[48],"still":[49],"introduce":[50],"new":[51],"length":[56],"bias":[57],"false":[59],"negative":[60,176],"sample":[61],"bias,":[62],"hinders":[64],"model's":[65],"ability":[66],"more":[69],"fine-grained":[70],"semantics.":[71],"In":[72],"paper,":[74],"we":[75],"reexamine":[76],"challenges":[78],"contrastive":[80,120,126,149],"from":[84],"a":[85,147],"debiasing":[86],"perspective":[87],"argue":[89],"effectively":[91],"eliminating":[92],"influence":[94],"various":[96],"is":[98,130],"crucial":[99],"for":[100,115,125,151],"high-quality":[102,173],"We":[105,145],"think":[106],"all":[107],"those":[108],"are":[110],"introduced":[111],"simple":[113],"rules":[114],"constructing":[116],"training":[117,136],"data":[118,137],"key":[124],"\"mimic\"":[132],"distribution":[134],"supervised":[139],"machine":[140],"way.":[144],"propose":[146],"novel":[148],"framework":[150],"embedding,":[153],"termed":[154],"DebCSE,":[155],"which":[156],"eliminate":[158],"impact":[160],"an":[165,206],"inverse":[166],"propensity":[167],"weighted":[168],"sampling":[169],"method":[170],"select":[172],"positive":[174],"pairs":[177],"according":[178],"both":[180],"surface":[182],"semantic":[184,191],"similarity":[185,193],"between":[186],"sentences.":[187],"Extensive":[188],"experiments":[189],"on":[190,213],"textual":[192],"(STS)":[194],"benchmarks":[195],"reveal":[196],"DebCSE":[198],"significantly":[199],"outperforms":[200],"latest":[202],"state-of-the-art":[203],"models":[204],"with":[205],"average":[207],"Spearman's":[208],"correlation":[209],"coefficient":[210],"80.33%":[212],"BERTbase.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-09-16T00:00:00"}