17.Interpretable Adversarial Perturbation in Input Embedding Space for Text
该文章对本人博客论文5.Adversarial Training Methods for Semi-Supervised Text Classification做了进一步的解释实验。 论文5针对NLP中半监督问题提出了解决的方案。 1.对抗训练是一种数剧增强的方法 ，即在原数据基础上求其一个最大的扰动，得到其对抗样本。 2.虚拟对抗是针对半监督学习，对于没有标签的那一部分，根据KL散度，生成其对抗
相关文章
- 1. 【深度学习NLP论文笔记】《Interpretable Adversarial Perturbation in Input Embedding Space for Text》
- 2. [Space Geodesy] Perturbation Theory
- 3. Adversarial Multi-task Learning for Text Classification
- 4. [解读] ClusterGAN : Latent Space Clustering in Generative Adversarial Networks
- 5. A Robust Adversarial Training Approach to Machine Reading Comprehension
- 6. 读书笔记17：Adversarial Attacks on Neural Networks for Graph Data
- 7. Generative Adversarial Text to Image Synthesis
- 8. [转] Implementing a CNN for Text Classification in TensorFlow
- 9. A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION
- 10. 30 Examples For Awk Command In Text Processing
- 更多相关文章...
- • Swift for-in 循环 - Swift 教程
- • XSLT
- • 为了进字节跳动，我精选了29道Java经典算法题，带详细讲解
- • Kotlin学习（一）基本语法
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 【深度学习NLP论文笔记】《Interpretable Adversarial Perturbation in Input Embedding Space for Text》
- 2. [Space Geodesy] Perturbation Theory
- 3. Adversarial Multi-task Learning for Text Classification
- 4. [解读] ClusterGAN : Latent Space Clustering in Generative Adversarial Networks
- 5. A Robust Adversarial Training Approach to Machine Reading Comprehension
- 6. 读书笔记17：Adversarial Attacks on Neural Networks for Graph Data
- 7. Generative Adversarial Text to Image Synthesis
- 8. [转] Implementing a CNN for Text Classification in TensorFlow
- 9. A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION
- 10. 30 Examples For Awk Command In Text Processing