{"id":"https://openalex.org/W3035683737","doi":"https://doi.org/10.1145/3397271.3401309","title":"Symmetric Regularization based BERT for Pair-wise Semantic Reasoning","display_name":"Symmetric Regularization based BERT for Pair-wise Semantic Reasoning","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3035683737","doi":"https://doi.org/10.1145/3397271.3401309","mag":"3035683737"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","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/A5103257775","display_name":"Weidi Xu","orcid":"https://orcid.org/0000-0002-7279-9339"},"institutions":[{"id":"https://openalex.org/I4210090985","display_name":"Zhejiang Financial College","ror":"https://ror.org/00deghz86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210090985"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weidi Xu","raw_affiliation_strings":["Ant Financial Services Group, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group, Shanghai, China","institution_ids":["https://openalex.org/I4210090985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074700282","display_name":"Xingyi Cheng","orcid":"https://orcid.org/0009-0005-4510-8693"},"institutions":[{"id":"https://openalex.org/I4210090985","display_name":"Zhejiang Financial College","ror":"https://ror.org/00deghz86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210090985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyi Cheng","raw_affiliation_strings":["Ant Financial Services Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group, Hangzhou, China","institution_ids":["https://openalex.org/I4210090985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055381638","display_name":"Kunlong Chen","orcid":"https://orcid.org/0000-0002-8828-9595"},"institutions":[{"id":"https://openalex.org/I4210090985","display_name":"Zhejiang Financial College","ror":"https://ror.org/00deghz86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210090985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunlong Chen","raw_affiliation_strings":["Ant Financial Services Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group, Hangzhou, China","institution_ids":["https://openalex.org/I4210090985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074676968","display_name":"Taifeng Wang","orcid":"https://orcid.org/0009-0007-1116-0228"},"institutions":[{"id":"https://openalex.org/I4210090985","display_name":"Zhejiang Financial College","ror":"https://ror.org/00deghz86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210090985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taifeng Wang","raw_affiliation_strings":["Ant Financial Services Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Ant Financial Services Group, Beijing, China","institution_ids":["https://openalex.org/I4210090985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103257775"],"corresponding_institution_ids":["https://openalex.org/I4210090985"],"apc_list":null,"apc_paid":null,"fwci":1.193,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83416724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1901","last_page":"1904"},"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":0.9997000098228455,"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":0.9950000047683716,"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":0.8101574182510376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7647252082824707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6841577291488647},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6354250311851501},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5354049205780029},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5290499925613403},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5130847692489624},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4894977807998657},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.48178693652153015},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.44147735834121704},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4408009350299835},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4225367605686188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25197798013687134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101574182510376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7647252082824707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6841577291488647},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6354250311851501},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5354049205780029},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5290499925613403},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5130847692489624},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4894977807998657},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.48178693652153015},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.44147735834121704},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4408009350299835},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4225367605686188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25197798013687134},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401309","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2951286828","https://openalex.org/W2963323070","https://openalex.org/W2963748441","https://openalex.org/W2963846996"],"related_works":["https://openalex.org/W4213275102","https://openalex.org/W2151138761","https://openalex.org/W2367925007","https://openalex.org/W3015724364","https://openalex.org/W4288263119","https://openalex.org/W2967994095","https://openalex.org/W2966892770","https://openalex.org/W2753909498","https://openalex.org/W4389010498","https://openalex.org/W2048025304"],"abstract_inverted_index":{"The":[0],"ability":[1,104],"of":[2,45,105,116],"semantic":[3,106],"reasoning":[4],"over":[5],"the":[6,37,60,77,94,98,103,114,145,148,158],"sentence":[7,39,88],"pair":[8],"is":[9,44],"essential":[10,61],"for":[11,48],"many":[12],"natural":[13,18],"language":[14,19],"understanding":[15],"tasks,":[16],"e.g.,":[17],"inference":[20],"and":[21,67,118,150],"machine":[22],"reading":[23],"comprehension.":[24],"A":[25],"recent":[26],"significant":[27],"improvement":[28,137],"in":[29,42],"these":[30],"tasks":[31],"comes":[32],"from":[33],"BERT.":[34,140],"As":[35],"reported,":[36],"next":[38],"prediction":[40,89],"(NSP)":[41],"BERT":[43],"great":[46],"significance":[47],"downstream":[49],"problems":[50],"with":[51],"sentence-pair":[52],"input.":[53],"Despite":[54],"its":[55],"effectiveness,":[56],"NSP":[57,78,117],"still":[58],"lacks":[59],"signal":[62],"to":[63,75,80,96],"distinguish":[64],"between":[65],"entailment":[66],"shallow":[68],"correlation.":[69],"To":[70],"remedy":[71],"this,":[72],"we":[73],"propose":[74],"augment":[76],"task":[79,92],"a":[81,111,123,154],"multi-class":[82],"categorization":[83],"task,":[84],"which":[85,126],"includes":[86,127],"previous":[87],"(PSP).":[90],"This":[91,132],"encourages":[93],"model":[95],"learn":[97],"subtle":[99],"semantics,":[100],"thereby":[101],"improves":[102,144],"understanding.":[107],"Furthermore,":[108],"by":[109,153],"using":[110],"smoothing":[112],"technique,":[113],"scopes":[115],"PSP":[119],"are":[120],"expanded":[121],"into":[122],"broader":[124],"range":[125],"close":[128],"but":[129],"nonsuccessive":[130],"sentences.":[131],"simple":[133],"method":[134,142],"yields":[135],"remarkable":[136],"against":[138],"vanilla":[139],"Our":[141],"consistently":[143],"performance":[146],"on":[147],"NLI":[149],"MRC":[151],"benchmarks":[152],"large":[155],"margin,":[156],"including":[157],"challenging":[159],"HANS":[160],"dataset.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}