From post

Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation.

, , , , , , , и . EMNLP (Findings), стр. 3685-3694. Association for Computational Linguistics, (2023)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

 

Другие публикации лиц с тем же именем

SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network., , , , , , , и . CoRR, (2023)Cross-Lingual Dependency Parsing by POS-Guided Word Reordering., , , , , и . EMNLP (Findings), том EMNLP 2020 из Findings of ACL, стр. 2938-2948. Association for Computational Linguistics, (2020)Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples., , , , , , и . ACL (Findings), стр. 1694-1707. Association for Computational Linguistics, (2022)Certified Robustness to Text Adversarial Attacks by Randomized MASK., , , и . Comput. Linguistics, 49 (2): 395-427 (июня 2023)Spiking Convolutional Neural Networks for Text Classification., , и . ICLR, OpenReview.net, (2023)Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation., , , , , , , и . EMNLP (Findings), стр. 3685-3694. Association for Computational Linguistics, (2023)Certified Robustness to Text Adversarial Attacks by Randomized MASK., , , , , и . CoRR, (2021)Weight Perturbation as Defense against Adversarial Word Substitutions., , , , , , и . EMNLP (Findings), стр. 7054-7063. Association for Computational Linguistics, (2022)Enhancing Unsupervised Semantic Parsing with Distributed Contextual Representations., , , , , , и . ACL (Findings), стр. 11454-11465. Association for Computational Linguistics, (2023)Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution., , , , , , , и . EMNLP (1), стр. 3137-3147. Association for Computational Linguistics, (2021)