Rasa Algorithm Whiteboard Response Selection

Summary

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 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 ... In this video, we'll try to find unexpected intents using the brand new UnexpectedIntentPolicy. It helps to have seen the previous ... Instead of debugging a model, it might be *much* more effective to consider debugging your data. In this video, we'll discuss ... This video is the second version of an original video. The content of the original video still holds true, but we decided to change ... The Universal Sentence Encoder is an embedding for sentences as opposed to words. There are a few interesting tricks that are ... What might an assistant do if it sees a text from a language that it isn't trained on? It might make assumptions because it's unlike ... It's easy to get distracted when you go down the rabbit hole of performance statistics. But! Not every impressive benchmark is ... 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 ... Bad labels make your benchmarks unreliable, so how might we find some? In this video, we'll try out one trick and we'll see if it ...