TextAttack with Jack Morris скачать в хорошем качестве

TextAttack with Jack Morris

TextAttack is a Python framework for attacking NLP models and augmenting text datasets. TextAttack allows users to find blind spots in their models by running different types of attacks. It provides a library of shared components that make it easy to recreate attacks from the literature and create totally new attacks. These components can also be used for different methods of NLP data augmentation. Jack Morris is a researcher at the University of Virginia curious about the limitations of state-of-the-art NLP models. He's part of a team researching the robustness of NLP models and helped build TextAttack. In the fall, he'll join the class of the 2021 Google AI residency. Follow him at http://jackxmorris.com/ Here's a link to the paper: https://arxiv.org/abs/2005.05909 and here's a link to the library: https://github.com/QData/TextAttack This presentation was a part of our Virtual Deep Learning Salon, to sign up for updates on these join our meetup and slack community! http://wandb.me/meetups http://wandb.me/fs 👩🏼‍🚀Weights and Biases: Record and visualize every detail of your research, collaborate easily, advance the state of the art - we’re always free for academics and open source projects. Email carey@wandb.com with any questions or feature suggestions. Blog: https://www.wandb.com/articles Gallery: See what you can create with W&B -https://app.wandb.ai/gallery Continue the conversation on our slack community - http://wandb.me/fs