Rasa Algorithm Whiteboard Starspace

Summary

In this video we'll highlight the main points of the The way the response selector is implemented in 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 is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ... Text translation is hard, especially when you've only gotten a small amount of data to work with. But still ... we may be interested in ... 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 Universal Sentence Encoder is an embedding for sentences as opposed to words. There are a few interesting tricks that are ... Countvectors are still an unsung hero in natural language processing. This is especially true in 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 video is the second version of an original video. The content of the original video still holds true, but we decided to change ... Typos are a common issue for NLU models. There are some tweaks you might do to your pipeline to combat them, but maybe it ... 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 ... When you're making a digital assistant you'll need more than just