no code implementations • 6 Jun 2024 • Yinting Wu, Pai Peng, Bo Cai, Le Li, .
Adversarial training methods commonly generate independent initial perturbation for adversarial samples from a simple uniform distribution, and obtain the training batch for the classifier without selection.
2 code implementations • 29 Oct 2022 • Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, Bo Cai
First, we focus on input construction for our RE model and propose an entity-based document-context filter to retain useful information in the given documents by using the bridge entities in the text paths.
no code implementations • 8 Aug 2022 • Yi Hu, Bo Cai, Yaoxiang Yu
By leveraging the residual interaction, a matching module is designed to preserve more code semantics and descriptive features, that enhances the adhesion between the code and its corresponding query text.