{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T11:23:19Z","timestamp":1768821799969,"version":"3.49.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013290","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2020AAA0106501"],"award-info":[{"award-number":["2020AAA0106501"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772302"],"award-info":[{"award-number":["61772302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3105013","type":"journal-article","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T20:37:14Z","timestamp":1631306234000},"page":"2930-2941","source":"Crossref","is-referenced-by-count":11,"title":["CSS-LM: A Contrastive Framework for Semi-Supervised Fine-Tuning of Pre-Trained Language Models"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9509-9573","authenticated-orcid":false,"given":"Yusheng","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yankai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2988-0083","authenticated-orcid":false,"given":"Zhengyan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7709-2543","authenticated-orcid":false,"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6011-6115","authenticated-orcid":false,"given":"Maosong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Mach Learn Res"},{"key":"ref38","article-title":"Clear: Contrastive learning for sentence representation","author":"wu","year":"2020"},{"key":"ref33","first-page":"6966","article-title":"Train no evil: Selective masking for task-guided pre-training","author":"gu","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref32","first-page":"5986","article-title":"Bert and pals: Projected attention layers for efficient adaptation in multi-task learning","author":"stickland","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"houlsby","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"7","author":"peters","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref37","first-page":"1601","article-title":"An unsupervised sentence embedding method by mutual information maximization","author":"zhang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process 2020"},{"key":"ref36","article-title":"A mutual information maximization perspective of language representation learning","author":"kong","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","article-title":"An efficient framework for learning sentence representations","author":"logeswaran","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref34","first-page":"8342","article-title":"Don’t stop pretraining: Adapt language models to domains and tasks","author":"gururangan","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref27","article-title":"Clinicalbert: Modeling clinical notes and predicting hospital readmission","author":"huang","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref2","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref20","article-title":"Cross-lingual language model pretraining","author":"lample","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref21","first-page":"5265","article-title":"What Does BERT with Vision Look At?","author":"li","year":"0"},{"key":"ref24","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"lu","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref23","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"su","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1360"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"ref56","article-title":"Multicore-Tsne","author":"ulyanov","year":"2016"},{"key":"ref55","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","author":"lee","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","article-title":"Revisiting few-sample bert fine-tuning","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref53","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"dodge","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_38"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref12","first-page":"5408","article-title":"Self-training improves pre-training for natural language understanding","author":"du","year":"0","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref13","article-title":"Supervised contrastive learning for pre-trained language model fine-tuning","author":"beliz","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref16","first-page":"127","article-title":"CokeBERT: Contextual knowledge selection and embedding towards enhanced pre-trained language models","author":"su","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref18","article-title":"Ernie: Enhanced representation through Knowledge Integration","author":"sun","year":"2019"},{"key":"ref19","first-page":"7170","article-title":"Coreferential reasoning learning for language representation","author":"ye","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref4","first-page":"11328","article-title":"Pegasus: Pre-training with extracted gap-sentences for abstractive summarization","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref8","first-page":"2895","article-title":"Matching the blanks: Distributional similarity for relation learning","author":"soares","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref7","article-title":"Towards a human-like open-domain chatbot","author":"adiwardana","year":"2020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1361"},{"key":"ref9","first-page":"3661","author":"peng","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1590"},{"key":"ref45","first-page":"18661","article-title":"Supervised contrastive learning","author":"khosla","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref48","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1234"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00202"},{"key":"ref41","article-title":"Contrastive multiview coding","author":"tian","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","author":"gutmann","year":"0","journal-title":"J Mach Learn Res"},{"key":"ref43","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","author":"mnih","year":"0","journal-title":"Proc Neural Inf Process Syst"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09535242.pdf?arnumber=9535242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:59Z","timestamp":1652194439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9535242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3105013","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}