{"id":"https://openalex.org/W4400651718","doi":"https://doi.org/10.1002/aisy.202300717","title":"Simple Data Transformations for Mitigating the Syntactic Similarity to Improve Sentence Embeddings at Supervised Contrastive Learning","display_name":"Simple Data Transformations for Mitigating the Syntactic Similarity to Improve Sentence Embeddings at Supervised Contrastive Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4400651718","doi":"https://doi.org/10.1002/aisy.202300717"},"language":"en","primary_location":{"id":"doi:10.1002/aisy.202300717","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202300717","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202300717","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202300717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104103761","display_name":"Minji Kim","orcid":"https://orcid.org/0009-0005-6441-0441"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Minji Kim","raw_affiliation_strings":["Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029144793","display_name":"Whanhee Cho","orcid":"https://orcid.org/0000-0003-2069-4508"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]},{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Whanhee Cho","raw_affiliation_strings":["Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea","School of Computing University of Utah  Utah 84112 USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"School of Computing University of Utah  Utah 84112 USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050599058","display_name":"Soohyeong Kim","orcid":"https://orcid.org/0000-0003-0121-3588"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soohyeong Kim","raw_affiliation_strings":["Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100677785","display_name":"Yong Suk Choi","orcid":"https://orcid.org/0000-0002-9042-0599"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yong Suk Choi","raw_affiliation_strings":["Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea","Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence Hanyang University  Seoul 04763 Republic of Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Computer Science Hanyang University  Seoul 04763 Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100677785","https://openalex.org/A5104103761"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":2750,"currency":"USD","value_usd":2750},"apc_paid":{"value":2750,"currency":"USD","value_usd":2750},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08608404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"8","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":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9979000091552734,"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":0.822029709815979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7202789187431335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6982303857803345},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5689818859100342},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5673526525497437},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4846108853816986},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.47701168060302734},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4682316184043884},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46799322962760925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822029709815979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7202789187431335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6982303857803345},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5689818859100342},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5673526525497437},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4846108853816986},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.47701168060302734},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4682316184043884},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46799322962760925},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/aisy.202300717","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202300717","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202300717","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4a8a2f150c634afb931e73a97bc948bf","is_oa":true,"landing_page_url":"https://doaj.org/article/4a8a2f150c634afb931e73a97bc948bf","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advanced Intelligent Systems, Vol 6, Iss 8, Pp n/a-n/a (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1002/aisy.202300717","is_oa":true,"landing_page_url":"https://doi.org/10.1002/aisy.202300717","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/aisy.202300717","source":{"id":"https://openalex.org/S4210212817","display_name":"Advanced Intelligent Systems","issn_l":"2640-4567","issn":["2640-4567"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G107372574","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G1474609591","display_name":null,"funder_award_id":"No.RS\u20102020\u2010II201373","funder_id":"https://openalex.org/F4320321142","funder_display_name":"Hanyang University"},{"id":"https://openalex.org/G29158475","display_name":null,"funder_award_id":"2020R1A2C1014037","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3034753964","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3897466587","display_name":null,"funder_award_id":"2020R1A2C1014037","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G44117325","display_name":null,"funder_award_id":"2018R1A5A7059549","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5051733337","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320321142","funder_display_name":"Hanyang University"},{"id":"https://openalex.org/G5323172026","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G7335664070","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8133777603","display_name":null,"funder_award_id":"2018R1A5A7059549","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400651718.pdf","grobid_xml":"https://content.openalex.org/works/W4400651718.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2014902591","https://openalex.org/W2114524997","https://openalex.org/W2160660844","https://openalex.org/W2163455955","https://openalex.org/W3011654523","https://openalex.org/W4212774754","https://openalex.org/W4285296644","https://openalex.org/W4294969216"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2114797768","https://openalex.org/W2380654781","https://openalex.org/W2176214140","https://openalex.org/W2516873349"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,19],"of":[2,35,103,124,151],"sentence":[3,62],"representations":[4],"has":[5],"achieved":[6],"great":[7],"improvements":[8],"in":[9,64,81,128,165,170],"several":[10],"natural":[11,24],"language":[12,25],"processing":[13],"tasks.":[14,117],"However,":[15],"the":[16,23,33,51,54,65,90,95,122,125,139,144,149,171],"supervised":[17,175],"contrastive":[18,176],"model":[20,140],"trained":[21],"on":[22,46,109,143],"inference":[26],"(NLI)":[27],"dataset":[28,67,173],"is":[29,39,59,107,155,163,180],"insufficient":[30],"to":[31,41,76,89,97,100,148],"elucidate":[32],"semantics":[34,167],"sentences":[36],"since":[37],"it":[38,58],"prone":[40],"make":[42],"a":[43,74,156],"prediction":[44],"based":[45],"heuristics.":[47],"Herein,":[48],"by":[49,134],"using":[50],"ParsEVAL":[52],"and":[53,72,92,115,131,136],"word":[55],"overlap":[56],"metric,":[57],"shown":[60],"that":[61,160],"pairs":[63],"NLI":[66,172],"have":[68],"strong":[69],"syntactic":[70,87],"similarity":[71,112],"propose":[73],"framework":[75],"compensate":[77],"for":[78],"this":[79],"problem":[80],"two":[82],"aspects.":[83],"1)":[84],"Apply":[85],"simple":[86],"transformations":[88],"hypothesis":[91],"2)":[93],"expand":[94],"objective":[96],"SupCon":[98],"Loss":[99],"leverage":[101],"variants":[102],"sentences.":[104],"The":[105,118,178],"method":[106],"evaluated":[108],"semantic":[110],"textual":[111],"(STS)":[113],"tasks":[114],"transfer":[116],"proposed":[119],"methods":[120],"improve":[121],"performance":[123,158],"BERT\u2010based":[126],"baseline":[127],"STS":[129],"Benchmark":[130],"SICK":[132],"Relatedness":[133],"1.48%":[135],"2.2%.":[137],"Furthermore,":[138],"achieves":[141],"82.65%":[142],"HANS":[145],"benchmark":[146],"dataset,":[147],"best":[150],"our":[152,161],"knowledge,":[153],"which":[154],"state\u2010of\u2010the\u2010art":[157],"demonstrating":[159],"approach":[162],"effective":[164],"grasping":[166],"without":[168],"heuristics":[169],"at":[174,182],"learning.":[177],"code":[179],"available":[181],"https://github.com/whnhch/Break-the-Similarity":[183],".":[184]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}