BERTGuard: Robust Text Classification against Adversarial Attacks
This paper introduces BERTGuard, a text classification framework that enhances the
resilience of BERT models against adversarial attacks through feature trimming and sub …
resilience of BERT models against adversarial attacks through feature trimming and sub …
MetaR: Few-Shot Named Entity Recognition With Meta-Learning and Relation Network
B Sun, K Gong, W Li, X Song - IEEE Transactions on Audio …, 2025 - ieeexplore.ieee.org
While conventional named entity recognition (NER) has achieved performance close to
human ability, few-shot NER research has seen little use. Few-shot NER aims to recognize …
human ability, few-shot NER research has seen little use. Few-shot NER aims to recognize …
Text classification method based on variational structure and dynamic weight optimization
W Cao, Z Qi, J Wang, L Liu - Proceedings of the 2024 2nd International …, 2024 - dl.acm.org
Given the problems that the fixed edge weight limits the expression ability of the model and
the inability to mine the structural features of high-dimensional graphs in the text …
the inability to mine the structural features of high-dimensional graphs in the text …