Rasa Algorithm Whiteboard Rulepolicy

In the age of deep learning and transformers, rule-based systems can still be a great idea. In this video, we hope to demonstrate ... This is the first video on attention mechanisms. We'll start with self attention and end with transformers. We're going at it step by ... In this video, we will discuss some technical details that are in the UnexpecTEDIntentPolicy. The UnexpecTEDIntentPolicy really is ... In the previous video, we've started measuring bias in word embeddings. In this video, we will attempt to remove some of this bias ... In this video we'll highlight the main points of the starspace paper. It's an influencial piece of work and here at This video explains the separate parts of the DIET architecture and how they are combined into an architecture that is useful in a ...

In this video, we'll highlight a qualitative argument of why you may not need to worry about pre-trained embeddings too much. When you iterate on your data, you also want to iterate on your model. It'd be a shame to have to retrain from scratch every single ... In this video we'd like to demonstrate an new tool that we've open-sourced. It's called "whatlies" and the goal of the package is to ... This is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ... In the previous video on bias, we showed that you should be careful with debiasing techniques. In this video, we zoom in on why ... What if we design a policy mechanism that doesn't predict the next action to take, but instead predicts when something ...

This is the fourth and final video on attention mechanisms. In the previous video we introduced multiheaded keys, queries and ...