{"id":"https://openalex.org/W4388405368","doi":"https://doi.org/10.1109/dsaa60987.2023.10302506","title":"TOCOL: Improving Contextual Representation of Pre-trained Language Models via Token-Level Contrastive Learning","display_name":"TOCOL: Improving Contextual Representation of Pre-trained Language Models via Token-Level Contrastive Learning","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4388405368","doi":"https://doi.org/10.1109/dsaa60987.2023.10302506"},"language":"en","primary_location":{"id":"doi:10.1109/dsaa60987.2023.10302506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsaa60987.2023.10302506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","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/A5082423788","display_name":"Keheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Keheng Wang","raw_affiliation_strings":["Beihang University,Sino-French Engineer School,Beijing,China","Sino-French Engineer School, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-French Engineer School,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sino-French Engineer School, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079167910","display_name":"Chuantao Yin","orcid":"https://orcid.org/0000-0002-0742-0804"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuantao Yin","raw_affiliation_strings":["Beihang University,Sino-French Engineer School,Beijing,China","Sino-French Engineer School, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-French Engineer School,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sino-French Engineer School, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114269634","display_name":"Rumei Li","orcid":"https://orcid.org/0009-0009-1264-5854"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rumei Li","raw_affiliation_strings":["NLP center Meituan.Inc,Beijing,China","NLP center Meituan.Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLP center Meituan.Inc,Beijing,China","institution_ids":["https://openalex.org/I4210152823"]},{"raw_affiliation_string":"NLP center Meituan.Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631506","display_name":"Sirui Wang","orcid":"https://orcid.org/0000-0001-9519-5741"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sirui Wang","raw_affiliation_strings":["NLP center Meituan.Inc,Beijing,China","NLP center Meituan.Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLP center Meituan.Inc,Beijing,China","institution_ids":["https://openalex.org/I4210152823"]},{"raw_affiliation_string":"NLP center Meituan.Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086726545","display_name":"Yunsen Xian","orcid":"https://orcid.org/0000-0002-5303-9641"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsen Xian","raw_affiliation_strings":["NLP center Meituan.Inc,Beijing,China","NLP center Meituan.Inc, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLP center Meituan.Inc,Beijing,China","institution_ids":["https://openalex.org/I4210152823"]},{"raw_affiliation_string":"NLP center Meituan.Inc, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055420596","display_name":"Wenge Rong","orcid":"https://orcid.org/0000-0002-4229-7215"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenge Rong","raw_affiliation_strings":["Beihang University,School of Computer Science and Engin,Beijing,China","School of Computer Science and Engin, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engin,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engin, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100442123","display_name":"Zhang Xiong","orcid":"https://orcid.org/0000-0002-9421-1014"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Xiong","raw_affiliation_strings":["Beihang University,School of Computer Science and Engin,Beijing,China","School of Computer Science and Engin, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,School of Computer Science and Engin,Beijing,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Computer Science and Engin, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5082423788"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14333457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"3"},"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/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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9865999817848206,"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":0.753979504108429},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6451812386512756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5604251027107239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5503506064414978},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5134938359260559},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5042723417282104},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48385488986968994},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.474464476108551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33925575017929077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753979504108429},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6451812386512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5604251027107239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5503506064414978},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5134938359260559},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5042723417282104},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48385488986968994},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.474464476108551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33925575017929077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsaa60987.2023.10302506","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/dsaa60987.2023.10302506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2923014074","https://openalex.org/W3105816068","https://openalex.org/W3156636935","https://openalex.org/W3175362188","https://openalex.org/W3192478068","https://openalex.org/W3213074177","https://openalex.org/W4223490341","https://openalex.org/W4287614078","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6784874100"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W3134175397","https://openalex.org/W4304700937"],"abstract_inverted_index":{"Self-attention,":[0],"which":[1,33,90],"allows":[2],"transformers":[3],"to":[4,35,47,96,100,109],"capture":[5,110],"deep":[6],"bidirectional":[7],"contexts,":[8],"plays":[9],"a":[10,76,92,134],"vital":[11],"role":[12],"in":[13,50],"BERT-like":[14],"pre-trained":[15,87],"language":[16,88],"models.":[17],"However,":[18],"the":[19,63,83,97,102,111,118,128,139],"maximum":[20],"likelihood":[21],"pre-training":[22],"objective":[23,95],"of":[24,65,86,114,141],"BERT":[25],"may":[26,60],"produce":[27],"an":[28],"anisotropic":[29],"word":[30,103],"embedding":[31],"space,":[32],"leads":[34],"biased":[36],"attention":[37,98],"scores":[38],"for":[39,81,144],"high-frequency":[40],"tokens,":[41],"as":[42],"they":[43],"are":[44],"very":[45],"close":[46],"each":[48],"other":[49],"representation":[51,85,104],"space":[52,105],"and":[53,106,137],"thus":[54],"have":[55],"higher":[56],"similarities.":[57],"This":[58],"bias":[59],"ultimately":[61],"affect":[62],"encoding":[64],"global":[66,112],"contextual":[67,84],"information.":[68],"To":[69],"address":[70],"this":[71],"issue,":[72],"we":[73,132],"propose":[74],"TOCOL,":[75],"TOken-Level":[77],"COntrastive":[78],"Learning":[79],"framework":[80],"improving":[82],"models,":[89],"integrates":[91],"novel":[93],"self-supervised":[94],"mechanism":[99],"reshape":[101],"encourages":[107],"PLM":[108],"semantics":[113],"sentences.":[115],"Results":[116],"on":[117],"GLUE":[119],"Benchmark":[120],"show":[121],"that":[122],"TOCOL":[123],"brings":[124],"considerable":[125],"improvement":[126],"over":[127],"original":[129],"BERT.":[130],"Furthermore,":[131],"conduct":[133],"detailed":[135],"analysis":[136],"demonstrate":[138],"robustness":[140],"our":[142],"approach":[143],"low-resource":[145],"scenarios.":[146]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}