1 code implementation • Findings (EMNLP) 2021 • Ruixuan Luo, Yi Zhang, Sishuo Chen, Xu sun
The nature of no word delimiter or inflection that can indicate segment boundaries or word semantics increases the difficulty of Chinese text understanding, and also intensifies the demand for word-level semantic knowledge to accomplish the tagging goal in Chinese segmenting and labeling tasks.
no code implementations • 13 Oct 2022 • Zhiyuan Zhang, Ruixuan Luo, Qi Su, Xu sun
It demonstrates that flat minima tend to imply better generalization abilities.
no code implementations • 7 Sep 2021 • Zhiyuan Zhang, Ruixuan Luo, Xuancheng Ren, Qi Su, Liangyou Li, Xu sun
To enhance neural networks, we propose the adversarial parameter defense algorithm that minimizes the average risk of multiple adversarial parameter corruptions.
1 code implementation • 25 Dec 2020 • Ruixuan Luo, Wei Li, Zhiyuan Zhang, Ruihan Bao, Keiko Harimoto, Xu sun
Recent deep learning based methods focus on learning clustering oriented representations.
1 code implementation • 10 Jun 2020 • Xu Sun, Zhiyuan Zhang, Xuancheng Ren, Ruixuan Luo, Liangyou Li
We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter.
2 code implementations • 27 Oct 2019 • Jianbang Ding, Xuancheng Ren, Ruixuan Luo, Xu sun
The dynamic learning rate bounds are based on the exponential moving averages of the adaptive learning rates themselves, which smooth out unexpected large learning rates and stabilize the training of deep neural networks.
4 code implementations • 27 Jun 2019 • Ruixuan Luo, Jingjing Xu, Yi Zhang, Zhiyuan Zhang, Xuancheng Ren, Xu sun
Through this method, we generate synthetic data using a large amount of unlabeled data in the target domain and then obtain a word segmentation model for the target domain.
no code implementations • 8 Sep 2018 • Ruixuan Luo
Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors.
4 code implementations • ECCV 2018 • Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, Yuning Jiang
The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes.
Ranked #172 on Object Detection on COCO test-dev