Rasa Algorithm Whiteboard Incremental Training

Summary

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 ... This is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ... In this video we'll highlight the main points of the starspace paper. It's an influencial piece of work and here at The way the response selector is implemented in In this video, we'll try to find unexpected intents using the brand new UnexpectedIntentPolicy. It helps to have seen the previous ... 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 ... Instead of debugging a model, it might be *much* more effective to consider debugging your data. In this video, we'll discuss ... This video explains the separate parts of the DIET architecture and how they are combined into an architecture that is useful in a ... We're starting a new playlist! Introducing the Sometimes you can change the intent labels to get a more accurate model. In this video, we will explore how to do this with 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 ... This video is the second version of an original video. The content of the original video still holds true, but we decided to change ... In the age of deep learning and transformers, rule-based systems can still be a great idea. In this video, we hope to demonstrate ... If you're just getting started with a virtual assistant you might be able to quickly get inspiration for intents/labels by using ...