{"id":"https://openalex.org/W4323520067","doi":"https://doi.org/10.1145/3578741.3578759","title":"Keyword Extractor for Contrastive Learning of Unsupervised Sentence Embedding","display_name":"Keyword Extractor for Contrastive Learning of Unsupervised Sentence Embedding","publication_year":2022,"publication_date":"2022-12-23","ids":{"openalex":"https://openalex.org/W4323520067","doi":"https://doi.org/10.1145/3578741.3578759"},"language":"en","primary_location":{"id":"doi:10.1145/3578741.3578759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578741.3578759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058753258","display_name":"Hua Cai","orcid":"https://orcid.org/0000-0002-7738-129X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hua Cai","raw_affiliation_strings":["UniDT, China"],"affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072814157","display_name":"Weihong Chen","orcid":"https://orcid.org/0000-0001-8216-2422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihong Chen","raw_affiliation_strings":["UniDT, China"],"affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089335994","display_name":"Kehuan Shi","orcid":"https://orcid.org/0000-0002-5439-7352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kehuan Shi","raw_affiliation_strings":["UniDT, China"],"affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084769892","display_name":"Shuaishuai Li","orcid":"https://orcid.org/0000-0002-4732-8981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuaishuai Li","raw_affiliation_strings":["UniDT, China"],"affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015319602","display_name":"Qing Xu","orcid":"https://orcid.org/0000-0002-3747-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Xu","raw_affiliation_strings":["UniDT, China"],"affiliations":[{"raw_affiliation_string":"UniDT, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058753258"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1379,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57718064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","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/T13083","display_name":"Advanced Text Analysis Techniques","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/T10028","display_name":"Topic Modeling","score":0.9847999811172485,"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":0.9681000113487244,"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":0.7570298314094543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6480699181556702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575062096118927},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5670487880706787},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5381214618682861},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.46466103196144104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05913171172142029}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570298314094543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6480699181556702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575062096118927},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5670487880706787},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5381214618682861},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.46466103196144104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05913171172142029},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3578741.3578759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578741.3578759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5187630019","display_name":null,"funder_award_id":"2021-GZL-RGZN-01020","funder_id":"https://openalex.org/F4320325413","funder_display_name":"Shanghai Municipal Commission of Economy and Informatization"}],"funders":[{"id":"https://openalex.org/F4320325413","display_name":"Shanghai Municipal Commission of Economy and Informatization","ror":"https://ror.org/04166ws88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1581231885","https://openalex.org/W2755266740","https://openalex.org/W2965276171","https://openalex.org/W2970641574","https://openalex.org/W2973226110","https://openalex.org/W3000623537","https://openalex.org/W3114537677","https://openalex.org/W6931636349"],"related_works":["https://openalex.org/W3082848404","https://openalex.org/W2081900870","https://openalex.org/W1979583797","https://openalex.org/W2016864125","https://openalex.org/W2372254676","https://openalex.org/W2080135837","https://openalex.org/W2793679056","https://openalex.org/W2375873920","https://openalex.org/W2597655663","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,7,75],"has":[2],"been":[3],"widely":[4],"applied":[5],"to":[6,24,87,150],"unsupervised":[8,15,154],"sentence":[9,64,77],"embedding.":[10],"One":[11,91],"major":[12],"method":[13],"is":[14,93,122],"SimCSE,":[16],"which":[17,69,152],"only":[18,71],"uses":[19],"random":[20],"dropouts":[21],"as":[22,109],"noise":[23],"build":[25],"positive":[26],"pairs":[27],"for":[28],"contrastive":[29],"learning.":[30],"But":[31],"token-level":[32],"matching":[33,53],"does":[34],"not":[35,70],"always":[36],"properly":[37],"represent":[38],"the":[39,51,59,73,88,94,102,106,113,116,123,138],"similarity":[40,52,147],"between":[41,55],"texts.":[42,56],"Sentence-level":[43],"semantic":[44,145],"representation":[45],"based":[46],"on":[47,144],"keyword-level":[48],"could":[49],"enhance":[50],"performance":[54],"To":[57],"emphasize":[58],"contribution":[60],"of":[61,76,84,97,105,115,126,142],"keywords":[62],"in":[63],"representation,":[65],"we":[66],"propose":[67],"KESimCSE,":[68],"includes":[72],"constrastive":[74],"embedding":[78,100,104],"but":[79],"also":[80],"adds":[81],"KL":[82],"divergence":[83],"two":[85],"elements":[86],"loss":[89],"function.":[90],"element":[92,121],"dot":[95],"product":[96],"each":[98],"token":[99],"and":[101],"[CLS]":[103,110],"BERT":[107],"outputs,":[108],"generally":[111],"captures":[112],"semantics":[114],"whole":[117],"sentence.":[118],"The":[119],"other":[120],"weight":[124],"list":[125],"all":[127],"tokens":[128],"obtained":[129],"through":[130],"keyword":[131],"extraction":[132],"method.":[133],"Our":[134],"experiments":[135],"show":[136],"that":[137],"averaged":[139],"Spearman\u2019s":[140],"correlation":[141],"KESimCSE":[143],"textual":[146],"tasks":[148],"raises":[149],"77.21%,":[151],"outperforms":[153],"SimCSE":[155],"by":[156],"nearly":[157],"1.30%.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}