Rasa Algorithm Whiteboard Rulepolicy

Summary

In the age of deep learning and transformers, rule-based systems can still be a great idea. In this video, we hope to demonstrate ... In this video we'd to demonstrate an new tool that we've open-sourced. It's called "whatlies" and the goal of the package is to ... How do you judge the quality of a virtual assistant? Can we look at the intent classification scores and call it a day? Or do we need ... When you're making a digital assistant you'll need more than just In this video, we will discuss some technical details that are in the UnexpecTEDIntentPolicy. The UnexpecTEDIntentPolicy really is ... This video explains the separate parts of the DIET architecture and how they are combined into an architecture that is useful in a ... It turns out that you can drop a lot of weights from your neural network without seeing a drastic effect on accuracy. In this video ... We're starting a new playlist! Introducing the This is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ... 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'll highlight a qualitative argument of why you may not need to worry about pre-trained embeddings too much. The way the response selector is implemented in Word Embeddings have a bias issue. In this video we'll explore what this means by looking at gender bias. We will try to find a ... This video is the second version of an original video. The content of the original video still holds true, but we decided to change ...