RETVec is a state-of-the-art text vectorizer which works directly on text inputs to create resilient classification models. Models trained with RETVec achieve better classification performance with fewer parameters and exhibit stronger resilience against adversarial attacks and typos, as reported in our paper.
Google is countering with RETVec (Resilient & Efficient Text Vectorizer). Open sourced by Google Research, this approach “helps models achieve state-of-the-art classification performance and drastically reduces computational cost,” while supporting “every language and all UTF-8 characters without the need for text preprocessing.” This makes it ideal for on-device, web, and other large-scale use cases:
t-Distributed Stochastic Neighbor Embedding (t-SNE) is a (prize-winning) technique for dimensionality reduction that is particularly well suited for the visualization of high-dimensional datasets. The technique can be implemented via Barnes-Hut approximations, allowing it to be applied on large real-world datasets. We applied it on data sets with up to 30 million examples. The technique and its variants are introduced in the following papers:
Bookmarks on this page are managed by an admin user. 