Corpus ID: 221949068

Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training

@article{Kitada2020AttentionMP,
  title={Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training},
  author={Shunsuke Kitada and H. Iyatomi},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.12064}
}

Shunsuke Kitada, H. Iyatomi

Published 2020

Computer Science

ArXiv

In recent years, deep learning models have placed more emphasis on the interpretability and robustness of models. The attention mechanism is an important technique that contributes to these elements and is widely used, especially in the natural language processing (NLP) field. Adversarial training (AT) is a powerful regularization technique for enhancing the robustness of neural networks and has been successful in many applications. The application of AT to the attention mechanism is expected… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed