Rasa Algorithm Whiteboard Transliteration

Summary

This video is a bit ... different. We'll be exploring a trick that sounds it might work, but we can only confirm it by receiving ... This is the second video on attention mechanisms. In the previous video we introduced self attention and in this video we're going ... 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 ... We're starting a new playlist! Introducing the We're making a few videos that highlight word embeddings. Before training word embeddings we figured it might help the intuition ... Countvectors are still an unsung hero in natural language processing. This is especially true in In this video we'll highlight the main points of the starspace paper. It's an influencial piece of work and here at Many pre-trained language models work on a single language. But in the conversational setting, we're usually dealing with a mix ... 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 ... The Universal Sentence Encoder is an embedding for sentences as opposed to words. There are a few interesting tricks that are ... 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 ... You might have heard about the `king - man + woman = queen` analogy. In this video we'll dive into the phenomenon of ... 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 ... In the age of deep learning and transformers, rule-based systems can still be a great idea. In this video, we hope to demonstrate ...